solidprivacy-nl commited on
Commit
afaecd9
·
1 Parent(s): f47c1b4

Correct care role preservation sidecar offsets

Browse files
corpus/care/care_role_preservation_seed_001.gold.json CHANGED
@@ -1,34 +1 @@
1
- {
2
- "document_id": "care_role_preservation_seed_001",
3
- "domain": "care",
4
- "document_type": "synthetic_care_role_preservation_note",
5
- "language": "nl",
6
- "source_file": "corpus/care/care_role_preservation_seed_001.txt",
7
- "synthetic": true,
8
- "labels": [
9
- {"id":"L001","entity_class":"PERSON","text":"Bakker","start":168,"end":174,"sensitivity":"direct_identifier","required":true,"acceptable_entity_types":["PERSON"],"notes":"Name after care role arts; role word remains context."},
10
- {"id":"L002","entity_class":"PERSON","text":"Sara El Idrissi","start":196,"end":211,"sensitivity":"direct_identifier","required":true,"acceptable_entity_types":["PERSON"],"notes":"Name after care role verpleegkundige."},
11
- {"id":"L003","entity_class":"PERSON","text":"Youssef Ait Ben","start":222,"end":237,"sensitivity":"direct_identifier","required":true,"acceptable_entity_types":["PERSON"],"notes":"Name after care role cliënt."},
12
- {"id":"L004","entity_class":"PERSON","text":"Fatima Zahra","start":269,"end":281,"sensitivity":"direct_identifier","required":true,"acceptable_entity_types":["PERSON"],"notes":"Name after care role Mantelzorger."},
13
- {"id":"L005","entity_class":"MEDICAL_OR_CARE_REFERENCE","text":"ZORG-CL-2026-77881","start":333,"end":351,"sensitivity":"care_reference","required":true,"acceptable_entity_types":["NL_HEALTHCARE_REFERENCE","NL_SUSPICIOUS_REFERENCE_CANDIDATE"],"notes":"Client care reference."},
14
- {"id":"L006","entity_class":"MEDICAL_OR_CARE_REFERENCE","text":"ZD-2026-11220","start":367,"end":380,"sensitivity":"care_reference","required":true,"acceptable_entity_types":["NL_HEALTHCARE_REFERENCE","NL_SUSPICIOUS_REFERENCE_CANDIDATE"],"notes":"Care dossier reference."},
15
- {"id":"L007","entity_class":"INCIDENT_NUMBER","text":"MIC-2026-6612","start":390,"end":403,"sensitivity":"incident_reference","required":true,"acceptable_entity_types":["NL_INCIDENT_NUMBER","NL_SUSPICIOUS_REFERENCE_CANDIDATE"],"notes":"Care incident reference."},
16
- {"id":"L008","entity_class":"MEDICAL_OR_CARE_REFERENCE","text":"98765432109","start":416,"end":427,"sensitivity":"professional_reference","required":true,"acceptable_entity_types":["NL_BIG_NUMBER","NL_HEALTHCARE_REFERENCE"],"notes":"BIG-number-like value."},
17
- {"id":"L009","entity_class":"EMAIL","text":"sara.elidrissi@example.test","start":429,"end":455,"sensitivity":"direct_identifier","required":true,"acceptable_entity_types":["EMAIL_ADDRESS"],"notes":"Reserved synthetic email domain."},
18
- {"id":"L010","entity_class":"PHONE","text":"06 11223344","start":459,"end":470,"sensitivity":"direct_identifier","required":true,"acceptable_entity_types":["PHONE_NUMBER","NL_PHONE_NUMBER"],"notes":"Synthetic mobile number."}
19
- ],
20
- "preserve_terms": [
21
- {"term":"cliënt","start":3,"end":9,"reason":"care role/context term"},
22
- {"term":"arts","start":36,"end":40,"reason":"care role/context term"},
23
- {"term":"verpleegkundige","start":45,"end":60,"reason":"care role/context term"},
24
- {"term":"zorgmedewerker","start":67,"end":81,"reason":"care role/context term"},
25
- {"term":"behandelaar","start":86,"end":97,"reason":"care role/context term"},
26
- {"term":"mantelzorger","start":117,"end":129,"reason":"care role/context term"}
27
- ],
28
- "known_traps": [
29
- {"text":"cliënt","trap_type":"care_role_word_must_not_be_person","notes":"Generic care role word should remain readable."},
30
- {"text":"arts","trap_type":"care_role_word_must_not_be_person","notes":"Generic professional role word should remain readable."},
31
- {"text":"behandelaar","trap_type":"care_role_word_must_not_be_person","notes":"Generic care role word should remain readable."},
32
- {"text":"mantelzorger","trap_type":"care_role_word_must_not_be_person","notes":"Generic care role word should remain readable."}
33
- ]
34
- }
 
1
+ {"document_id":"care_role_preservation_seed_001","domain":"care","document_type":"synthetic_care_role_preservation_note","language":"nl","source_file":"corpus/care/care_role_preservation_seed_001.txt","synthetic":true,"labels":[{"id":"L001","entity_class":"PERSON","text":"Bakker","start":168,"end":174,"sensitivity":"direct_identifier","required":true,"acceptable_entity_types":["PERSON"],"notes":"Name after care role arts; role word remains context."},{"id":"L002","entity_class":"PERSON","text":"Sara El Idrissi","start":195,"end":210,"sensitivity":"direct_identifier","required":true,"acceptable_entity_types":["PERSON"],"notes":"Name after care role verpleegkundige."},{"id":"L003","entity_class":"PERSON","text":"Youssef Ait Ben","start":221,"end":236,"sensitivity":"direct_identifier","required":true,"acceptable_entity_types":["PERSON"],"notes":"Name after care role cliënt."},{"id":"L004","entity_class":"PERSON","text":"Fatima Zahra","start":264,"end":276,"sensitivity":"direct_identifier","required":true,"acceptable_entity_types":["PERSON"],"notes":"Name after care role Mantelzorger."},{"id":"L005","entity_class":"MEDICAL_OR_CARE_REFERENCE","text":"ZORG-CL-2026-77881","start":323,"end":341,"sensitivity":"care_reference","required":true,"acceptable_entity_types":["NL_HEALTHCARE_REFERENCE","NL_SUSPICIOUS_REFERENCE_CANDIDATE"],"notes":"Client care reference."},{"id":"L006","entity_class":"MEDICAL_OR_CARE_REFERENCE","text":"ZD-2026-11220","start":357,"end":370,"sensitivity":"care_reference","required":true,"acceptable_entity_types":["NL_HEALTHCARE_REFERENCE","NL_SUSPICIOUS_REFERENCE_CANDIDATE"],"notes":"Care dossier reference."},{"id":"L007","entity_class":"INCIDENT_NUMBER","text":"MIC-2026-6612","start":381,"end":394,"sensitivity":"incident_reference","required":true,"acceptable_entity_types":["NL_INCIDENT_NUMBER","NL_SUSPICIOUS_REFERENCE_CANDIDATE"],"notes":"Care incident reference."},{"id":"L008","entity_class":"MEDICAL_OR_CARE_REFERENCE","text":"98765432109","start":407,"end":418,"sensitivity":"professional_reference","required":true,"acceptable_entity_types":["NL_BIG_NUMBER","NL_HEALTHCARE_REFERENCE"],"notes":"BIG-number-like value."},{"id":"L009","entity_class":"EMAIL","text":"sara.elidrissi@example.test","start":420,"end":447,"sensitivity":"direct_identifier","required":true,"acceptable_entity_types":["EMAIL_ADDRESS"],"notes":"Reserved synthetic email domain."},{"id":"L010","entity_class":"PHONE","text":"06 11223344","start":451,"end":462,"sensitivity":"direct_identifier","required":true,"acceptable_entity_types":["PHONE_NUMBER","NL_PHONE_NUMBER"],"notes":"Synthetic mobile number."}],"preserve_terms":[{"term":"cliënt","start":3,"end":9,"reason":"care role/context term"},{"term":"arts","start":37,"end":41,"reason":"care role/context term"},{"term":"verpleegkundige","start":46,"end":61,"reason":"care role/context term"},{"term":"zorgmedewerker","start":68,"end":82,"reason":"care role/context term"},{"term":"behandelaar","start":87,"end":98,"reason":"care role/context term"},{"term":"mantelzorger","start":116,"end":128,"reason":"care role/context term"}],"known_traps":[{"text":"cliënt","trap_type":"care_role_word_must_not_be_person","notes":"Generic care role word should remain readable."},{"text":"arts","trap_type":"care_role_word_must_not_be_person","notes":"Generic professional role word should remain readable."},{"text":"behandelaar","trap_type":"care_role_word_must_not_be_person","notes":"Generic care role word should remain readable."},{"text":"mantelzorger","trap_type":"care_role_word_must_not_be_person","notes":"Generic care role word should remain readable."}]}