glam/data/custodian/VN-HN-HAN-R-HNPRC.yaml
kempersc f284e87d13 feat: add 24,963 heritage custodian records from global extraction
Major batch addition of heritage institution data:
- Japan: 12,077 institutions (libraries, museums, archives)
- Czechia: 6,760 institutions
- Switzerland: 2,390 institutions
- Belgium: 448 institutions
- Belarus: 257 institutions
- Austria: 249 institutions (with corrected GHCIDs)
- Argentina: 235 institutions (bibliotecas populares)
- Brazil: 155 institutions
- Mexico: 110 institutions
- Bulgaria: 98 institutions
- Chile: 83 institutions
- Egypt: 50 institutions
- And additional records from VN, NL, GE, KR, GB, FR, US, IN, etc.

All records include:
- Standardized GHCID identifiers (alphabetic-only abbreviations)
- GeoNames-resolved location data
- ISO 3166-2 region codes
- Provenance metadata with extraction timestamps
2025-12-07 14:24:48 +01:00

123 lines
4.4 KiB
YAML

original_entry:
name: Han-Nom Preservation and Research Centre
institution_type: RESEARCH_CENTER
source: CH-Annotator (vietnamese_glam_institutions_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: Website
identifier_value: http://www.hannom.org.vn
identifier_url: http://www.hannom.org.vn
locations:
- city: Hanoi
country: VN
processing_timestamp: '2025-12-06T23:35:59.038800+00:00'
ghcid:
ghcid_current: VN-HN-HAN-R-HNPRC
ghcid_original: VN-XX-HAN-R-HNPRC
ghcid_uuid: 3798dd29-d970-5338-a0fb-b1a9edaacb21
ghcid_uuid_sha256: 6a81c40b-e0d1-87e1-bea5-aad654711b30
ghcid_numeric: 7674630795311527905
record_id: f6d39f4e-3ef9-451e-942e-af852db5342a
generation_timestamp: '2025-12-06T23:35:59.038800+00:00'
location_resolution:
country_code: VN
region_code: HN
city_code: HAN
method: GEONAMES_CITY_LOOKUP
region_name: VN-HN
geonames_id: 1581130
resolution_timestamp: '2025-12-07T12:09:57.193190+00:00'
ghcid_history:
- ghcid: VN-XX-HAN-R-HNPRC
ghcid_numeric: 7674630795311527905
valid_from: '2025-12-06T23:35:59.038800+00:00'
reason: Initial GHCID from CH-Annotator (vietnamese_glam_institutions_ch_annotator.yaml)
- ghcid: VN-HN-HAN-R-HNPRC
valid_from: '2025-12-07T12:09:57.193193+00:00'
reason: 'Region resolved via GeoNames city lookup: XX->HN (Hanoi)'
custodian_name:
claim_type: custodian_name
claim_value: Han-Nom Preservation and Research Centre
source_type: ch_annotator
identifiers:
- identifier_scheme: GHCID
identifier_value: VN-XX-HAN-R-HNPRC
- identifier_scheme: GHCID_UUID
identifier_value: 3798dd29-d970-5338-a0fb-b1a9edaacb21
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 6a81c40b-e0d1-87e1-bea5-aad654711b30
- identifier_scheme: GHCID_NUMERIC
identifier_value: '7674630795311527905'
- identifier_scheme: RECORD_ID
identifier_value: f6d39f4e-3ef9-451e-942e-af852db5342a
- *id001
provenance:
data_source: CONVERSATION_NLP
data_tier: TIER_4_INFERRED
extraction_date: '2025-11-09T00:00:00Z'
extraction_method: 'Created from CH-Annotator file: vietnamese_glam_institutions_ch_annotator.yaml'
confidence_score: 0.94
ch_annotator:
convention_id: ch_annotator-v1_7_0
convention_version: 1.7.0
entity_classification:
hypernym: GRP
hypernym_label: GROUP
subtype: GRP.HER.RES
subtype_label: RESEARCH_CENTER
ontology_class: schema:ResearchOrganization
alternative_classes:
- org:FormalOrganization
- rov:RegisteredOrganization
- glam:HeritageCustodian
extraction_provenance:
namespace: glam
path: /conversations/2025-09-22T14-42-00-85de0e0a-2274-4594-aa9c-58c1c00e804f
timestamp: '2025-11-09T00:00:00Z'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
annotation_provenance:
annotation_agent: opencode-claude-sonnet-4
annotation_date: '2025-12-06T21:13:54.700766+00:00'
annotation_method: retroactive CH-Annotator application via batch script
source_file: vietnamese_glam_institutions.yaml
annotation_metadata:
confidence_score: 0.94
verified: false
verification_date: null
verified_by: null
entity_claims:
- claim_type: full_name
claim_value: Han-Nom Preservation and Research Centre
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /conversations/2025-09-22T14-42-00-85de0e0a-2274-4594-aa9c-58c1c00e804f
timestamp: '2025-11-09T00:00:00Z'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.94
- claim_type: institution_type
claim_value: RESEARCH_CENTER
property_uri: rdf:type
provenance:
namespace: glam
path: /conversations/2025-09-22T14-42-00-85de0e0a-2274-4594-aa9c-58c1c00e804f
timestamp: '2025-11-09T00:00:00Z'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: located_in_city
claim_value: Hanoi
property_uri: schema:addressLocality
provenance:
namespace: glam
path: /conversations/2025-09-22T14-42-00-85de0e0a-2274-4594-aa9c-58c1c00e804f
timestamp: '2025-11-09T00:00:00Z'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.9
integration_note:
created_from: vietnamese_glam_institutions_ch_annotator.yaml
creation_date: '2025-12-06T23:35:59.038800+00:00'
creation_method: create_custodian_from_ch_annotator.py