Datasets:
id stringlengths 5 9 | span stringlengths 2 3.1k | schema listlengths 0 15 | entities listlengths 0 36 | excluded listlengths 0 68 | reasoning stringlengths 1 8.76k | reasoning_source stringclasses 2
values | native_thinking stringlengths 0 8.53k | raw_response stringlengths 55 9.59k | gold unknown |
|---|---|---|---|---|---|---|---|---|---|
ner_2 | Historic shipwreck identified in Lake Michigan
MUSKEGON – The bottom of Lake Michigan is literally a graveyard of shipwrecks. Local maritime historians say 1,200 of the 2,000 sunken vessels in Lake Michigan no longer exist because they hit shore and broke apart. Experts add that about 360 wrecks have been found in the... | [
"Location",
"Organization",
"Person",
"Date",
"Vessel",
"Event"
] | [
{
"text": "MUSKEGON",
"label": "Location",
"reason": "Capitalized city name mentioned as a location"
},
{
"text": "Lake Michigan",
"label": "Location",
"reason": "Specific lake name mentioned repeatedly"
},
{
"text": "Michigan Shipwreck Research Association",
"label": "Organi... | [
{
"text": "steamship",
"reason": "Common noun referring to a general category"
},
{
"text": "barreled flour",
"reason": "Descriptive phrase referring to cargo type"
},
{
"text": "ice floes",
"reason": "General environmental description"
}
] | I'll analyze the text to identify named entities following the given procedure.
First pass: This text is about a historic shipwreck discovered in Lake Michigan. It mentions specific names of people, places, organizations, and the ship itself, so it does contain named entities.
Looking at the text in order:
1. "MUSKE... | native_thinking_fallback | I'll analyze the text to identify named entities following the given procedure.
First pass: This text is about a historic shipwreck discovered in Lake Michigan. It mentions specific names of people, places, organizations, and the ship itself, so it does contain named entities.
Looking at the text in order:
1. "MUSKE... | <think>
I'll analyze the text to identify named entities following the given procedure.
First pass: This text is about a historic shipwreck discovered in Lake Michigan. It mentions specific names of people, places, organizations, and the ship itself, so it does contain named entities.
Looking at the text in order:
1... | {
"LOCATION": [
"Lake Michigan",
"MUSKEGON",
"Lake Michigan",
"Lake Michigan",
"shore",
"Muskegon",
"Lake Michigan",
"Lake Michigan",
"Milwaukee",
"Muskegon"
],
"OBJECT": [
"shipwrecks",
"vessels",
"wrecks",
"water",
"wrecks",
"steamship",
"wreck... |
ner_1 | Juho Haapoja
Juho Haapoja (born 22 October 1980) is a Finnish former professional boxer who competed from 2006 to 2017, and held the European Union cruiserweight title twice between 2011 and 2017. Professional career
Haapoja made his professional debut on 8 April 2006, losing a four-round points decision to Remigijus ... | [
"Person",
"Country",
"Organization"
] | [
{
"text": "Juho Haapoja",
"label": "Person",
"reason": "Named individual with biographical details provided"
},
{
"text": "Finland",
"label": "Country",
"reason": "Nationality explicitly stated in the text"
},
{
"text": "European Union",
"label": "Organization",
"reason":... | [
{
"text": "22 October 1980",
"reason": "Birthdate is a literal fact, not a named entity"
},
{
"text": "WBC and PABA",
"reason": "Abbreviations not expanded in the text"
},
{
"text": "Finnish heavyweight title",
"reason": "Generic title referencing Finland, not a distinct entity"
}
... | Okay, let's start by reading through the text about Juho Haapoja. The first thing I notice is that the text is about a Finnish former professional boxer. His name is clearly mentioned at the beginning: "Juho Haapoja". That seems like a clear named entity, probably a Person.
Next, there's a birth date: "born 22 October... | native_thinking_fallback | Okay, let's start by reading through the text about Juho Haapoja. The first thing I notice is that the text is about a Finnish former professional boxer. His name is clearly mentioned at the beginning: "Juho Haapoja". That seems like a clear named entity, probably a Person.
Next, there's a birth date: "born 22 October... | <think>
Okay, let's start by reading through the text about Juho Haapoja. The first thing I notice is that the text is about a Finnish former professional boxer. His name is clearly mentioned at the beginning: "Juho Haapoja". That seems like a clear named entity, probably a Person.
Next, there's a birth date: "born 22... | {
"PERSON": [
"Juho Haapoja",
"Juho Haapoja",
"Remigijus Ziausys",
"Jari Markkanen",
"Denis Bakhtov",
"Sami Elovaara",
"Jarno Rosberg",
"Faisal Ibnel Arrami",
"Ian Tims",
"Francesco Versaci",
"Mateusz Masternak"
],
"ORGANIZATION": [
"European Union",
"WBC",
... |
ner_4 | Scarce events of mitochondrial introgression in Trypanosoma cruzi: new case with a Bolivian strain. Trypanosoma cruzi, the agent of Chagas disease, presents a predominantly clonal structure that has been shaped by recombination events leading to six genetic groups (DTUs, discrete typing units, TcI-TcVI). Several conven... | [
"Species",
"Disease",
"Location",
"GeneticGroup",
"Method"
] | [
{
"text": "Trypanosoma cruzi",
"label": "Species",
"reason": "Explicitly named as the biological agent."
},
{
"text": "Chagas disease",
"label": "Disease",
"reason": "Directly identified as the disease caused by Trypanosoma cruzi."
},
{
"text": "Bolivian strain",
"label": "Lo... | [
{
"text": "strains",
"reason": "Generic noun referring to multiple instances, not a specific entity."
},
{
"text": "genotype",
"reason": "Descriptive term, not a named entity."
},
{
"text": "recombination events",
"reason": "Conceptual process, not a named entity."
}
] | The text discusses mitochondrial introgression in Trypanosoma cruzi, focusing on genetic analysis of strains from Bolivia and Peru. It identifies named entities primarily in scientific domains and geographic references.
1. **"Trypanosoma cruzi"** is explicitly named as the agent of Chagas disease and is a species-le... | visible | Okay, let's tackle this. The user wants me to generate synthetic reasoning data for training a model on open-schema NER. The text is about mitochondrial introgression in Trypanosoma cruzi.
First, I need to read through the text to see if there are any named entities. The text mentions specific strains and departments.... | <think>
Okay, let's tackle this. The user wants me to generate synthetic reasoning data for training a model on open-schema NER. The text is about mitochondrial introgression in Trypanosoma cruzi.
First, I need to read through the text to see if there are any named entities. The text mentions specific strains and depa... | {
"ORGANISM": [
"Trypanosoma cruzi",
"Trypanosoma cruzi",
"Triatoma infestans"
],
"NATIONALITY": [
"Bolivian",
"Bolivian",
"Peruvian"
],
"DISEASE": [
"Chagas disease"
],
"ABBREVIATION": [
"DTUs",
"TcI-TcVI",
"MLMT",
"DTUs",
"DTUs TcIII, IV, V, and VI",
"... |
ner_5 | Show SMILESO[C@@H]1[C@@H](COP(O)(=O)OP(O)(=O)OP(O)(O)=O)OC([C@@H]1O)n1cnc2c(NCCCCCNC(=O)CI)ncnc12
Show InChIInChI=1S/C17H28IN6O14P3/c18-6-11(25)19-4-2-1-3-5-20-15-12-16(22-8-21-15)24(9-23-12)17-14(27)13(26)10(36-17)7-35-40(31,32)38-41(33,34)37-39(28,29)30/h8-10,13-14,17,26-27H,1-7H2,(H,19,25)(H,31,32)(H,33,34)(H,20,21... | [] | [] | [
{
"text": "SMILES",
"reason": "Part of chemical notation system SMILES, not a named entity"
},
{
"text": "InChI",
"reason": "Part of chemical notation system InChI, not a named entity"
},
{
"text": "C",
"reason": "Chemical symbol for carbon, not a named entity"
},
{
"text": "... | I'll analyze the given text for named entities according to the specified procedure.
First, I'll read through the text to determine if it contains any named entities:
The text appears to be a chemical structure representation, specifically:
1. A SMILES notation: SMILESO[C@@H]1[C@@H](COP(O)(=O)OP(O)(=O)OP(O)(O)=O)OC([... | native_thinking_fallback | I'll analyze the given text for named entities according to the specified procedure.
First, I'll read through the text to determine if it contains any named entities:
The text appears to be a chemical structure representation, specifically:
1. A SMILES notation: SMILESO[C@@H]1[C@@H](COP(O)(=O)OP(O)(=O)OP(O)(O)=O)OC([... | <think>
I'll analyze the given text for named entities according to the specified procedure.
First, I'll read through the text to determine if it contains any named entities:
The text appears to be a chemical structure representation, specifically:
1. A SMILES notation: SMILESO[C@@H]1[C@@H](COP(O)(=O)OP(O)(=O)OP(O)(O... | {
"CHEMICAL_COMPOUND": [
"SMILESO[C@@H]1[C@@H](COP(O)(=O)OP(O)(=O)OP(O)(O)=O)OC([C@@H]1O)n1cnc2c(NCCCCCNC(=O)CI)ncnc12",
"25",
"22-8-21-15",
"24",
"27",
"26",
"36-17",
"31",
"32",
"38-41(",
"33,",
"34)",
"37-39(",
"28,",
"29)",
"30",
"17",
"19",
... |
ner_3 | Gino Mäder
Gino Mäder (born 4 January 1997) is a Swiss road and track cyclist, who currently rides for UCI WorldTeam . He competed at the 2016 UEC European Track Championships in the team pursuit event. Major results
2014
4th Road race, European Junior Road Championships
9th Overall Grand Prix Rüebliland
9th Overa... | [
"Person",
"Nationality",
"Organization",
"Event"
] | [
{
"text": "Gino Mäder",
"label": "Person",
"reason": "Full name stated as cyclist's identity"
},
{
"text": "Swiss",
"label": "Nationality",
"reason": "Demonym describing cyclist's origin"
},
{
"text": "UCI WorldTeam",
"label": "Organization",
"reason": "Named sports team ... | [
{
"text": "road and track cyclist",
"reason": "Generic role description, not a named entity"
},
{
"text": "2014",
"reason": "Year marker without distinct entity status"
},
{
"text": "Time trial",
"reason": "Race discipline, not standalone entity"
}
] | Okay, let's start by reading through the text provided. The text is about Gino Mäder, a Swiss cyclist. The first sentence mentions his name and birthdate, stating he's a road and track cyclist riding for a UCI WorldTeam. The next sentence talks about his participation in the 2016 UEC European Track Championships.
Look... | native_thinking_fallback | Okay, let's start by reading through the text provided. The text is about Gino Mäder, a Swiss cyclist. The first sentence mentions his name and birthdate, stating he's a road and track cyclist riding for a UCI WorldTeam. The next sentence talks about his participation in the 2016 UEC European Track Championships.
Look... | <think>
Okay, let's start by reading through the text provided. The text is about Gino Mäder, a Swiss cyclist. The first sentence mentions his name and birthdate, stating he's a road and track cyclist riding for a UCI WorldTeam. The next sentence talks about his participation in the 2016 UEC European Track Championship... | {
"PERSON": [
"Gino Mäder",
"Gino Mäder"
],
"NATIONALITY": [
"Swiss",
"Swiss",
"Swiss"
],
"SPORTS_TEAM": [
"UCI WorldTeam"
],
"SPORTS_EVENT": [
"2016 UEC European Track Championships",
"European Junior Road Championships",
"Grand Prix Rüebliland",
"Tour du Pays de V... |
ner_6 | using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using SenseNet.ContentRepository.Schema;
using SenseNet.ContentRepository.Storage;
namespace SenseNet.ContentRepository
{
/// <summary>
/// A Content handler class that can contain child Contents, usually technical... | [
"Namespace",
"Class"
] | [
{
"text": "SenseNet.ContentRepository",
"label": "Namespace",
"reason": "Fully qualified namespace name representing a software library/module"
},
{
"text": "SystemFolder",
"label": "Class",
"reason": "Class defined within the framework's namespace, explicitly discussed as a type"
}
] | [
{
"text": "System",
"reason": "Standard .NET namespace, not a named entity"
},
{
"text": "parent",
"reason": "Generic parameter name"
},
{
"text": "nodeTypeName",
"reason": "Generic parameter name"
},
{
"text": "Folder",
"reason": "Common noun/base type"
}
] | The text is a C# code snippet defining a class within the `SenseNet.ContentRepository` namespace. Namespaces and class names in code are often syntactic elements rather than named entities unless they denote specific frameworks, libraries, or components.
1. **Namespace `SenseNet.ContentRepository`**: This is a fully ... | visible | Okay, let's tackle this text. The user provided a C# code snippet from what looks like a .NET project, specifically part of the SenseNet.ContentRepository namespace. My task is to determine if there are any named entities here following the given guidelines.
First, I'll read through the text once. The code includes na... | <think>
Okay, let's tackle this text. The user provided a C# code snippet from what looks like a .NET project, specifically part of the SenseNet.ContentRepository namespace. My task is to determine if there are any named entities here following the given guidelines.
First, I'll read through the text once. The code inc... | {
"CONTENTHANDLER": [
"System",
"System",
"System",
"System",
"system"
],
"TYPE": [
"SystemFolder",
"Folder",
"SystemFolder",
"SystemFolder",
"Node",
"SystemFolder",
"node",
"SystemFolder",
"Node",
"SystemFolder"
],
"VARIABLE": [
"parent",
"p... |
ner_9 | The growth in use of credit and debit cards has been met with a rise in fraud and theft. To improve the customer experience, merchants often relax security standards during transactions. As an example, a merchant may require only a credit card number, expiration date, and security code, but not evidence of possession o... | [] | [] | [
{
"text": "credit card",
"reason": "generic category, not a specific named entity"
},
{
"text": "merchant",
"reason": "role or general term, not a specific organization or person"
},
{
"text": "security code",
"reason": "descriptive phrase referring to a standard component of payment... | The text discusses general practices and issues related to credit/debit card usage and fraud but does not mention any specific named entities. Terms like "credit cards," "debit cards," "merchants," and "security standards" are categories or roles, not specific instances. No proper nouns, organizations, locations, or ot... | visible | Okay, let's start by reading through the text carefully. The passage is about the growth in credit and debit card usage leading to fraud and theft. It mentions how merchants relax security standards during transactions, like not requiring proof of possession of the actual card. The entities here seem to be general term... | <think>
Okay, let's start by reading through the text carefully. The passage is about the growth in credit and debit card usage leading to fraud and theft. It mentions how merchants relax security standards during transactions, like not requiring proof of possession of the actual card. The entities here seem to be gene... | {
"PRODUCT": [
"debit cards",
"actual credit card"
],
"CRIME": [
"fraud",
"theft"
],
"PROFESSION": [
"merchants"
],
"CONCEPT": [
"security standards",
"credit card number",
"expiration date",
"security code",
"possession",
"information"
],
"EVENT": [
"tr... |
ner_10 | {
"name": "Wuhan ShenZhiDu KeJi YouXian GongSi",
"displayName": "Wuhan ShenZhiDu KeJi YouXian GongSi",
"properties": [
"deepin.org"
]
} | [
"Company",
"Domain"
] | [
{
"text": "Wuhan ShenZhiDu KeJi YouXian GongSi",
"label": "Company",
"reason": "Full legal name of a Chinese limited liability company, structured with location (Wuhan), brand (ShenZhiDu), and corporate form (KeJi YouXian GongSi)"
},
{
"text": "deepin.org",
"label": "Domain",
"reason": "... | [] | Okay, let's start by looking at the given text. The text is a JSON object with keys "name", "displayName", and "properties". The value for "name" and "displayName" is "Wuhan ShenZhiDu KeJi YouXian GongSi". The "properties" array contains "deepin.org".
First, I need to determine if there are any named entities here. T... | native_thinking_fallback | Okay, let's start by looking at the given text. The text is a JSON object with keys "name", "displayName", and "properties". The value for "name" and "displayName" is "Wuhan ShenZhiDu KeJi YouXian GongSi". The "properties" array contains "deepin.org".
First, I need to determine if there are any named entities here. T... | <think>
Okay, let's start by looking at the given text. The text is a JSON object with keys "name", "displayName", and "properties". The value for "name" and "displayName" is "Wuhan ShenZhiDu KeJi YouXian GongSi". The "properties" array contains "deepin.org".
First, I need to determine if there are any named entities... | {
"COMPANY": [
"Wuhan ShenZhiDu KeJi YouXian GongSi",
"Wuhan ShenZhiDu KeJi YouXian GongSi"
],
"WEBSITE": [
"deepin.org"
]
} |
ner_7 | Q:
How does backtracking affect the language recognized by a parser? Not a school related question, but it comes up in the Dragon Book (Compilers: Principles, Techniques, and Tools) in an exercise:
The grammar:
S ::= aSa | aa
generates all even length strings of a's except for the empty string. a) Construct a recursiv... | [
"BookTitle",
"BookSection",
"ProgrammingLanguage"
] | [
{
"text": "Dragon Book",
"label": "BookTitle",
"reason": "The text explicitly references 'Compilers: Principles, Techniques, and Tools' as the Dragon Book, a well-known textbook title"
},
{
"text": "Exercise 4.13",
"label": "BookSection",
"reason": "The text cites a specific exercise wit... | [
{
"text": "recursive-descent parser",
"reason": "A general technical term describing a parsing strategy, not a specific named entity"
},
{
"text": "S ::= aSa | aa",
"reason": "A grammar rule presented in the text, not a named entity"
}
] | Okay, let me start by looking at the given text. The user is asking about backtracking in parsers and a specific grammar from the Dragon Book. The main question is about how backtracking affects the language recognized by a parser.
First, I need to check if there are any named entities in the text. The text mentions t... | native_thinking_fallback | Okay, let me start by looking at the given text. The user is asking about backtracking in parsers and a specific grammar from the Dragon Book. The main question is about how backtracking affects the language recognized by a parser.
First, I need to check if there are any named entities in the text. The text mentions t... | <think>
Okay, let me start by looking at the given text. The user is asking about backtracking in parsers and a specific grammar from the Dragon Book. The main question is about how backtracking affects the language recognized by a parser.
First, I need to check if there are any named entities in the text. The text me... | {
"TECHNIQUE": [
"backtracking",
"backtracking",
"backtracking"
],
"CONCEPT": [
"language",
"language"
],
"CHARACTER": [
"a",
"a",
"a",
"a",
"a",
"a",
"a",
"A",
"a"
],
"TOOL": [
"parser",
"recursive-descent",
"parser",
"procedure for ... |
ner_8 | Kenworthy has several points of disagreement with the Vermont senator, but both basically argue that the United States should adopt polices similar to those of Scandinavian countries in which the government provides more resources for parents and the economically insecure. In his book "Social Democratic America," Kenwo... | [
"Person",
"Location",
"Work",
"GovernmentProgram"
] | [
{
"text": "Kenworthy",
"label": "Person",
"reason": "Repeated reference to an individual's arguments and book"
},
{
"text": "Vermont",
"label": "Location",
"reason": "State name used in political context"
},
{
"text": "United States",
"label": "Location",
"reason": "Full ... | [
{
"text": "Vermont senator",
"reason": "Role descriptor, not proper name"
},
{
"text": "governmental insurance",
"reason": "Generic concept phrase"
},
{
"text": "working-class families",
"reason": "Descriptive demographic phrase"
},
{
"text": "AD",
"reason": "Likely text ... | Okay, let's start by reading through the text carefully. The user wants me to identify named entities based on explicit reasoning. First, I need to determine if there are any actual named entities here.
The text mentions "Kenworthy" multiple times. Since it's a surname used to refer to a specific person (probably the ... | native_thinking_fallback | Okay, let's start by reading through the text carefully. The user wants me to identify named entities based on explicit reasoning. First, I need to determine if there are any actual named entities here.
The text mentions "Kenworthy" multiple times. Since it's a surname used to refer to a specific person (probably the ... | <think>
Okay, let's start by reading through the text carefully. The user wants me to identify named entities based on explicit reasoning. First, I need to determine if there are any actual named entities here.
The text mentions "Kenworthy" multiple times. Since it's a surname used to refer to a specific person (proba... | {
"PERSON": [
"Kenworthy",
"Kenworthy",
"Kenworthy",
"President Obama"
],
"LOCATION": [
"Vermont",
"United States",
"Scandinavian countries"
],
"ORGANIZATION": [
"government",
"government",
"government",
"Social Security",
"Medicare"
],
"TITLE": [
"Socia... |
ner_31 | Transition zone defect associated with the response to proton pump inhibitor treatment in patients with globus sensation. Few data describing short-term proton pump inhibitor (PPI) treatment in patients with globus sensation exist. The aim of this study was to evaluate the use of high-resolution manometry (HRM) for pre... | [] | [] | [] | <think> | visible | <think>
```json
{"entities": [], "excluded": []}
``` | {
"TREATMENT": [
"proton pump inhibitor",
"proton pump inhibitor"
],
"GROUP": [
"patients",
"patients",
"patients",
"patients",
"patients",
"patients",
"patients",
"patients",
"patients",
"GERD patients"
],
"CONDITION": [
"globus sensation",
"globus sens... | |
ner_24 | NEO
NEO
$ 7.02
Price USD
0.95 %
Last hour
8.86 %
Last day
What is NEO? NEO is a non-profit, community-based blockchain project. It is a distributed network that uses blockchain technology and digital identities to digitize assets and uses smart contracts to automate digital assets and realize "smart economy." | [
"BlockchainProject"
] | [
{
"text": "NEO",
"label": "BlockchainProject",
"reason": "The text describes 'NEO' as a specific blockchain project"
}
] | [] | <think>
I'm
The text is a single sentence describing "NEO" as a blockchain project. The term "NEO" appears twice as the subject, followed by a description of its nature and purpose. The first mention of "NEO" is capitalized and used as a proper noun referring to a specific entity. The subsequent appearances are con... | visible | <think>
I'm
The text is a single sentence describing "NEO" as a blockchain project. The term "NEO" appears twice as the subject, followed by a description of its nature and purpose. The first mention of "NEO" is capitalized and used as a proper noun referring to a specific entity. The subsequent appearances are con... | {
"CRYPTOCURRENCY": [
"NEO",
"NEO",
"NEO",
"NEO"
],
"CURRENCY": [
"USD"
],
"TECHNOLOGY": [
"blockchain project",
"digital identities",
"smart contracts"
],
"CONCEPT": [
"smart economy"
]
} | |
ner_27 | What is the difference between the Department of Systems Biology and the Center for Computational Biology and Bioinformatics? In recognition of the importance of systems biology to the future of biological and biomedical research, the Trustess of Columbia University approved the creation of the Department of Systems Bi... | [
"AcademicDepartment",
"ResearchCenter",
"University",
"Initiative"
] | [
{
"text": "Department of Systems Biology",
"label": "AcademicDepartment",
"reason": "Explicitly named academic department at Columbia University"
},
{
"text": "Center for Computational Biology and Bioinformatics",
"label": "ResearchCenter",
"reason": "Named research center within the dep... | [
{
"text": "systems biology",
"reason": "General academic field term, not a specific entity"
},
{
"text": "computational biology",
"reason": "General discipline term, not a specific entity"
},
{
"text": "bioinformatics",
"reason": "General technical field term"
}
] | Okay, let's tackle this problem step by step. First, I need to determine if the given text contains any named entities. The text is about the Department of Systems Biology and the Center for Computational Biology and Bioinformatics at Columbia University.
Starting with the first sentence, it mentions "Department of S... | native_thinking_fallback | Okay, let's tackle this problem step by step. First, I need to determine if the given text contains any named entities. The text is about the Department of Systems Biology and the Center for Computational Biology and Bioinformatics at Columbia University.
Starting with the first sentence, it mentions "Department of S... | <think>
Okay, let's tackle this problem step by step. First, I need to determine if the given text contains any named entities. The text is about the Department of Systems Biology and the Center for Computational Biology and Bioinformatics at Columbia University.
Starting with the first sentence, it mentions "Departm... | {
"ORGANIZATION": [
"Department of Systems Biology",
"Center for Computational Biology and Bioinformatics",
"Columbia University",
"Department of Systems Biology",
"Center of Computational Biology and Bioinformatics",
"Department of Systems Biology",
"Department of Systems Biology",
"C... |
ner_25 | Nursing internships: a tri-state survey and model for evaluation. Results of a survey of 14 nursing internship programs are presented, and discussed. The results indicate that objective and systematic evaluation of the derived costs and benefits of these programs is often not considered. A methodology is described and ... | [] | [] | [
{
"text": "tri-state survey",
"reason": "descriptive phrase without specific identity or referent"
},
{
"text": "nursing internship programs",
"reason": "generic category reference"
}
] | The text discusses a survey of nursing internship programs and proposes an evaluation methodology. I first scan for any plausible named entities. The phrase "tri-state survey" appears in the title, but "tri-state" here is a descriptive term referring to three-state regions, not a specific named entity (no states are na... | visible | Okay, let's see. So the user wants me to act as the teacher, right? My job is to generate reasoning data for training a model to do open-schema named entity recognition. Hmm. The key here is to follow the procedure step by step.
First, I need to read the text once and decide if it has any named entities. The text prov... | <think>
Okay, let's see. So the user wants me to act as the teacher, right? My job is to generate reasoning data for training a model to do open-schema named entity recognition. Hmm. The key here is to follow the procedure step by step.
First, I need to read the text once and decide if it has any named entities. The t... | {
"PROGRAM": [
"Nursing internships"
],
"SURVEY": [
"tri-state survey"
],
"METHODOLOGY": [
"model",
"evaluation",
"evaluation",
"model"
],
"BENEFIT": [
"costs",
"benefits"
],
"EFFECTIVENESS": [
"program effectiveness"
]
} |
ner_26 | Q:
How to store every search term to Database in Django
I have a search form on my website. When the user types a query (like iPhone) the program will store that keyword to a database called "SearchTerms" with the number of people who searched for that keyword. Example:
search_term: iPhone
search_count: 50
which me... | [
"Technology",
"Brand"
] | [
{
"text": "Django",
"label": "Technology",
"reason": "Specific Python-based web framework"
},
{
"text": "iPhone",
"label": "Brand",
"reason": "Example search term referring to Apple's product line"
}
] | [
{
"text": "search term",
"reason": "Generic term describing user input"
},
{
"text": "database",
"reason": "Common noun referring to data storage system"
},
{
"text": "SearchTerms",
"reason": "User-defined database name, not a real-world entity"
},
{
"text": "search_count",
... | The text discusses storing search terms in a Django application, with an example search term "iPhone." The primary candidate entities are "Django" and "iPhone."
- **Django** is mentioned as the framework used for the website. It refers to the specific Python-based web framework, making it a Technology entity.
- **iPh... | visible | Okay, let's see. Okay, let's go through this step by step. The user is asking how to store search terms in a Django database. The text mentions "iPhone" as an example search term. So first, I need to check if there are any named entities here. The main part is the example given: "search_term: iPhone" and "search_count:... | <think>
Okay, let's see. Okay, let's go through this step by step. The user is asking how to store search terms in a Django database. The text mentions "iPhone" as an example search term. So first, I need to check if there are any named entities here. The main part is the example given: "search_term: iPhone" and "searc... | {
"FRAMEWORK": [
"Django"
],
"PRODUCT": [
"iPhone",
"iPhone",
"iPhone"
]
} |
ner_30 | What You Should Know About Printers This Year
It is not easy to obtain a barcode scanner that will serve the needs you have. The selection of the right barcode scanner will be possible when you consider several factors. The consideration of quality and price of barcode scanner will indicate that they are not equal. Th... | [] | [] | [
{
"text": "barcode scanner",
"reason": "generic noun phrase referring to a category of devices, not a specific named entity"
},
{
"text": "a barcode scanner",
"reason": "common noun phrase with indefinite article, not a proper name"
},
{
"text": "good budget",
"reason": "descriptive ... | The text begins with a statement that "many texts contain no entities at all," implying that the current text might belong to that category. However, the presence of the word "barcode scanner" suggests a potential entity, though it's a common noun phrase referring to a category of devices rather than a specific named e... | native_thinking_fallback | The text begins with a statement that "many texts contain no entities at all," implying that the current text might belong to that category. However, the presence of the word "barcode scanner" suggests a potential entity, though it's a common noun phrase referring to a category of devices rather than a specific named e... | <think>
The text begins with a statement that "many texts contain no entities at all," implying that the current text might belong to that category. However, the presence of the word "barcode scanner" suggests a potential entity, though it's a common noun phrase referring to a category of devices rather than a specific... | {
"PRODUCT": [
"barcode scanner",
"barcode scanner",
"barcode scanner",
"barcode scanner",
"barcode scanner",
"barcode scanner",
"barcode scanner",
"barcode scanner",
"barcode scanner",
"barcode scanner",
"barcode scanner"
],
"ATTRIBUTE": [
"quality",
"price",
... |
ner_29 | [Functional results obtained by radium contact irradiation of the glottic carcinoma]. 45 patients having been treated with radium contact irradiation on account of a glottic carcinoma were continually checked up with a view to ascertaining the functional results obtained. By means of indirect and direct laryngoscopy as... | [] | [] | [] | Okay, let's see. The user wants me to generate synthetic reasoning data for training a model to do open-schema named entity recognition. The key points are to follow the procedure outlined, which involves reading the text, identifying entities based on the content without inventing them, choosing specific labels, handl... | native_thinking_fallback | Okay, let's see. The user wants me to generate synthetic reasoning data for training a model to do open-schema named entity recognition. The key points are to follow the procedure outlined, which involves reading the text, identifying entities based on the content without inventing them, choosing specific labels, handl... | <think>
Okay, let's see. The user wants me to generate synthetic reasoning data for training a model to do open-schema named entity recognition. The key points are to follow the procedure outlined, which involves reading the text, identifying entities based on the content without inventing them, choosing specific label... | {
"TREATMENT": [
"radium contact irradiation",
"radium contact irradiation"
],
"DISEASE": [
"glottic carcinoma",
"glottic carcinoma"
],
"PERSON": [
"patients"
],
"TEST": [
"direct laryngoscopy",
"stroboscopy"
],
"ANATOMY": [
"vocal organ"
],
"ATTRIBUTE": [
"voca... |
ner_32 | Toxigenic saprophytic fungi in marine shellfish farming areas. Toxigenic saprophytic fungi were isolated from samples of shellfish, sediment and seawater obtained from marine shellfish farming areas. The 456 strains identified included 12 different genera, with a clear predominance (68%) of Penicillium, Aspergillus, Tr... | [
"BiologicalTaxon",
"BiologicalSpecies"
] | [
{
"text": "Penicillium",
"label": "BiologicalTaxon",
"reason": "Scientific name of a fungal genus"
},
{
"text": "Aspergillus",
"label": "BiologicalTaxon",
"reason": "Scientific name of a fungal genus"
},
{
"text": "Trichoderma",
"label": "BiologicalTaxon",
"reason": "Scie... | [] | <think>
The text mentions a scientific study on toxigenic fungi found in marine shellfish farming areas. I'll analyze the content to identify any named entities.
Starting with the first sentence, "Toxigenic saprophytic fungi in marine shellfish farming areas" describes a general topic, not specific named entities... | visible | <think>
The text mentions a scientific study on toxigenic fungi found in marine shellfish farming areas. I'll analyze the content to identify any named entities.
Starting with the first sentence, "Toxigenic saprophytic fungi in marine shellfish farming areas" describes a general topic, not specific named entities... | {
"ORGANISM": [
"Toxigenic saprophytic",
"fungi",
"Toxigenic saprophytic",
"fungi",
"shellfish",
"Penicillium",
"Aspergillus",
"Trichoderma",
"Cladosporium",
"fungi",
"shellfish",
"larvae of Artemia salina",
"fungi",
"shellfish",
"filter-feeding shellfish",
... |
Open-Schema Teacher Reasoning on Pile-NER
Part of the code, data and models of the bachelor thesis Structuring Universal Chain-of-thought for Named Entity Recognition (Department of Computer Science and Engineering, University of Bologna, 2026). All the repositories cited by name belong to the same organization.
Raw, unfiltered open-schema Chain-of-Thought extractions generated by the teacher (Qwen3-32B, 4-bit) on Pile-NER passages: 43,231 rows, before any jury filtering. 34,419 rows come from the AWQ checkpoint sampled with temperature 0.6, top-p 0.95, top-k 20 and a presence penalty of 1.5; the other 8,812 from an earlier run with a bitsandbytes 4-bit quantization and no presence penalty.
Each row contains id, span (the Pile-NER text), gold (Pile-NER
annotation, type → spans), schema, reasoning (teacher CoT), entities
(extracted entities with type and reason), excluded (candidates the teacher
rejected, with reason), raw_response, native_thinking and
reasoning_source: visible (23,816 rows, reasoning written in the answer)
or native_thinking_fallback (19,415 rows, reasoning recovered from the
model's <think> block).
The jury scores and the accepted subset are in jury.
- Downloads last month
- 65