Hugging Face's logo

Spaces:
solidprivacy
/
scrub
Sleeping

App Files Community
solidprivacy-nl commited on
Commit
327019c
·
1 Parent(s): 1826bcc

Add legal reference gold sidecar

Browse files
Files changed (1) hide show
  1. corpus/legal/legal_reference_seed_001.gold.json +281 -0
corpus/legal/legal_reference_seed_001.gold.json ADDED
@@ -0,0 +1,281 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "document_id": "legal_reference_seed_001",
3
+ "domain": "legal",
4
+ "document_type": "synthetic_legal_reference_note",
5
+ "language": "nl",
6
+ "source_file": "corpus/legal/legal_reference_seed_001.txt",
7
+ "synthetic": true,
8
+ "labels": [
9
+ {
10
+ "id": "L001",
11
+ "entity_class": "CASE_NUMBER",
12
+ "text": "10598721 / UE VERZ 26-441",
13
+ "start": 11,
14
+ "end": 36,
15
+ "sensitivity": "matter_reference",
16
+ "required": true,
17
+ "acceptable_entity_types": [
18
+ "NL_LEGAL_CASE_NUMBER",
19
+ "NL_SUSPICIOUS_REFERENCE_CANDIDATE"
20
+ ],
21
+ "notes": "Rechtspraak-like rolnummer value only."
22
+ },
23
+ {
24
+ "id": "L002",
25
+ "entity_class": "CASE_NUMBER",
26
+ "text": "ARN 26/4412",
27
+ "start": 86,
28
+ "end": 97,
29
+ "sensitivity": "matter_reference",
30
+ "required": true,
31
+ "acceptable_entity_types": [
32
+ "NL_LEGAL_CASE_NUMBER",
33
+ "NL_SUSPICIOUS_REFERENCE_CANDIDATE"
34
+ ]
35
+ },
36
+ {
37
+ "id": "L003",
38
+ "entity_class": "CASE_NUMBER",
39
+ "text": "ZK-WOON-55091",
40
+ "start": 116,
41
+ "end": 129,
42
+ "sensitivity": "matter_reference",
43
+ "required": true,
44
+ "acceptable_entity_types": [
45
+ "NL_LEGAL_CASE_NUMBER",
46
+ "NL_SUSPICIOUS_REFERENCE_CANDIDATE"
47
+ ]
48
+ },
49
+ {
50
+ "id": "L004",
51
+ "entity_class": "CLIENT_NUMBER",
52
+ "text": "CL-FAM-55201",
53
+ "start": 169,
54
+ "end": 181,
55
+ "sensitivity": "client_reference",
56
+ "required": true,
57
+ "acceptable_entity_types": [
58
+ "NL_CLIENT_REFERENCE",
59
+ "NL_SUSPICIOUS_REFERENCE_CANDIDATE"
60
+ ]
61
+ },
62
+ {
63
+ "id": "L005",
64
+ "entity_class": "CLIENT_NUMBER",
65
+ "text": "CLNT-2026-0042",
66
+ "start": 205,
67
+ "end": 219,
68
+ "sensitivity": "client_reference",
69
+ "required": true,
70
+ "acceptable_entity_types": [
71
+ "NL_CLIENT_REFERENCE",
72
+ "NL_SUSPICIOUS_REFERENCE_CANDIDATE"
73
+ ]
74
+ },
75
+ {
76
+ "id": "L006",
77
+ "entity_class": "DOSSIER_NUMBER",
78
+ "text": "DOS-2026-778899",
79
+ "start": 235,
80
+ "end": 250,
81
+ "sensitivity": "dossier_reference",
82
+ "required": true,
83
+ "acceptable_entity_types": [
84
+ "NL_DOSSIER_NUMBER",
85
+ "NL_SUSPICIOUS_REFERENCE_CANDIDATE"
86
+ ]
87
+ },
88
+ {
89
+ "id": "L007",
90
+ "entity_class": "CLIENT_NUMBER",
91
+ "text": "WR-KLANT-2026-7712",
92
+ "start": 285,
93
+ "end": 303,
94
+ "sensitivity": "client_reference",
95
+ "required": true,
96
+ "acceptable_entity_types": [
97
+ "NL_CLIENT_REFERENCE",
98
+ "NL_SUSPICIOUS_REFERENCE_CANDIDATE"
99
+ ]
100
+ },
101
+ {
102
+ "id": "L008",
103
+ "entity_class": "CLAIM_NUMBER",
104
+ "text": "FACT-2026-4481",
105
+ "start": 313,
106
+ "end": 327,
107
+ "sensitivity": "administrative_reference",
108
+ "required": true,
109
+ "acceptable_entity_types": [
110
+ "NL_INVOICE_NUMBER",
111
+ "NL_SUSPICIOUS_REFERENCE_CANDIDATE"
112
+ ]
113
+ },
114
+ {
115
+ "id": "L009",
116
+ "entity_class": "INCIDENT_NUMBER",
117
+ "text": "CAM-MAAS-2026-0518",
118
+ "start": 336,
119
+ "end": 354,
120
+ "sensitivity": "evidence_reference",
121
+ "required": true,
122
+ "acceptable_entity_types": [
123
+ "NL_OTHER_REFERENCE",
124
+ "NL_SUSPICIOUS_REFERENCE_CANDIDATE"
125
+ ]
126
+ },
127
+ {
128
+ "id": "L010",
129
+ "entity_class": "INCIDENT_NUMBER",
130
+ "text": "INC-2026-0912",
131
+ "start": 365,
132
+ "end": 378,
133
+ "sensitivity": "incident_reference",
134
+ "required": true,
135
+ "acceptable_entity_types": [
136
+ "NL_INCIDENT_NUMBER",
137
+ "NL_SUSPICIOUS_REFERENCE_CANDIDATE"
138
+ ]
139
+ },
140
+ {
141
+ "id": "L011",
142
+ "entity_class": "CLAIM_NUMBER",
143
+ "text": "REP-2026-4410",
144
+ "start": 392,
145
+ "end": 405,
146
+ "sensitivity": "repair_reference",
147
+ "required": true,
148
+ "acceptable_entity_types": [
149
+ "NL_OTHER_REFERENCE",
150
+ "NL_SUSPICIOUS_REFERENCE_CANDIDATE"
151
+ ]
152
+ },
153
+ {
154
+ "id": "L012",
155
+ "entity_class": "CLAIM_NUMBER",
156
+ "text": "CLM-2026-112233",
157
+ "start": 444,
158
+ "end": 459,
159
+ "sensitivity": "claim_reference",
160
+ "required": true,
161
+ "acceptable_entity_types": [
162
+ "NL_CLAIM_NUMBER",
163
+ "NL_SUSPICIOUS_REFERENCE_CANDIDATE"
164
+ ],
165
+ "notes": "Must not be PHONE_NUMBER."
166
+ },
167
+ {
168
+ "id": "L013",
169
+ "entity_class": "ECLI",
170
+ "text": "ECLI:NL:RBAMS:2026:1234",
171
+ "start": 470,
172
+ "end": 493,
173
+ "sensitivity": "matter_reference",
174
+ "required": true,
175
+ "acceptable_entity_types": [
176
+ "NL_ECLI",
177
+ "ECLI"
178
+ ]
179
+ },
180
+ {
181
+ "id": "L014",
182
+ "entity_class": "PERSON",
183
+ "text": "Noor van Dijk",
184
+ "start": 499,
185
+ "end": 512,
186
+ "sensitivity": "direct_identifier",
187
+ "required": true,
188
+ "acceptable_entity_types": [
189
+ "PERSON"
190
+ ]
191
+ },
192
+ {
193
+ "id": "L015",
194
+ "entity_class": "PERSON",
195
+ "text": "Sami El Amrani",
196
+ "start": 531,
197
+ "end": 545,
198
+ "sensitivity": "direct_identifier",
199
+ "required": true,
200
+ "acceptable_entity_types": [
201
+ "PERSON"
202
+ ]
203
+ },
204
+ {
205
+ "id": "L016",
206
+ "entity_class": "PHONE",
207
+ "text": "06-12345678",
208
+ "start": 550,
209
+ "end": 561,
210
+ "sensitivity": "direct_identifier",
211
+ "required": true,
212
+ "acceptable_entity_types": [
213
+ "PHONE_NUMBER",
214
+ "NL_PHONE_NUMBER"
215
+ ]
216
+ },
217
+ {
218
+ "id": "L017",
219
+ "entity_class": "EMAIL",
220
+ "text": "sami.elamrani@example.test",
221
+ "start": 565,
222
+ "end": 591,
223
+ "sensitivity": "direct_identifier",
224
+ "required": true,
225
+ "acceptable_entity_types": [
226
+ "EMAIL_ADDRESS"
227
+ ]
228
+ },
229
+ {
230
+ "id": "L018",
231
+ "entity_class": "ADDRESS",
232
+ "text": "Parklaan 188, 3512 ZX Utrecht",
233
+ "start": 615,
234
+ "end": 644,
235
+ "sensitivity": "direct_identifier",
236
+ "required": true,
237
+ "acceptable_entity_types": [
238
+ "LOCATION",
239
+ "ADDRESS"
240
+ ]
241
+ },
242
+ {
243
+ "id": "L019",
244
+ "entity_class": "NL_POSTCODE",
245
+ "text": "3512 ZX",
246
+ "start": 629,
247
+ "end": 636,
248
+ "sensitivity": "direct_identifier",
249
+ "required": true,
250
+ "acceptable_entity_types": [
251
+ "NL_POSTCODE"
252
+ ]
253
+ }
254
+ ],
255
+ "preserve_terms": [
256
+ {
257
+ "term": "Zaaknummer",
258
+ "start": 0,
259
+ "end": 10,
260
+ "reason": "label/context term; value should be detected, not the label"
261
+ },
262
+ {
263
+ "term": "Dossiernummer",
264
+ "start": 221,
265
+ "end": 234,
266
+ "reason": "label/context term; value should be detected, not the label"
267
+ }
268
+ ],
269
+ "known_traps": [
270
+ {
271
+ "text": "7:669 BW",
272
+ "trap_type": "legal_article_must_not_be_case_number",
273
+ "notes": "Legal article reference should not be treated as matter reference."
274
+ },
275
+ {
276
+ "text": "EUR 250,00",
277
+ "trap_type": "money_amount_must_not_be_reference",
278
+ "notes": "Money amount should not be treated as reference."
279
+ }
280
+ ]
281
+ }