glam/data/custodian/CZ-72-MEL-M-RMM.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

166 lines
5.5 KiB
YAML

original_entry:
name: Regionální muzeum Mělník
institution_type: MUSEUM
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: ARON_UUID
identifier_value: d6253348-66ce-42e9-9e18-489377ae97d9
identifier_url: https://portal.nacr.cz/aron/apu/d6253348-66ce-42e9-9e18-489377ae97d9
- &id002
identifier_scheme: INSTITUTION_CODE
identifier_value: '901206020'
- &id003
identifier_scheme: Wikidata
identifier_value: Q12049106
identifier_url: https://www.wikidata.org/wiki/Q12049106
- &id004
identifier_scheme: VIAF
identifier_value: '138181268'
identifier_url: https://viaf.org/viaf/138181268
locations: []
processing_timestamp: '2025-12-06T23:37:44.730969+00:00'
ghcid:
ghcid_current: CZ-72-MEL-M-RMM
ghcid_original: XX-XX-XXX-M-RMM
ghcid_uuid: ee2fc2a8-6b81-5af6-8403-81f2d1b94c44
ghcid_uuid_sha256: 22a5b0df-8029-8ca5-9998-9fcfa97142c5
ghcid_numeric: 2496596042421218469
record_id: 2bb2af3b-3a7a-4644-b199-f3037e0bd086
generation_timestamp: '2025-12-06T23:37:44.730969+00:00'
location_resolution:
country_code: CZ
region_code: '72'
city_code: MEL
method: CH_ANNOTATOR_TOP_SET
resolution_timestamp: '2025-12-07T00:19:31.882218+00:00'
city_name: Melnik
geonames_id: 3070862
feature_code: PPL
extracted_toponym: Mělník
latitude: 50.3505
longitude: 14.47411
ghcid_history:
- ghcid: XX-XX-XXX-M-RMM
ghcid_numeric: 2496596042421218469
valid_from: '2025-12-06T23:37:44.730969+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
- ghcid: CZ-XX-XXX-M-RMM
valid_from: '2025-12-06T23:54:39.261536+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-72-MEL-M-RMM
valid_from: '2025-12-07T00:19:31.882224+00:00'
reason: 'Location resolved via CH-Annotator TOP.SET extraction: Mělník -> Melnik
(GeoNames:3070862)'
custodian_name:
claim_type: custodian_name
claim_value: Regionální muzeum Mělník
source_type: ch_annotator
identifiers:
- identifier_scheme: GHCID
identifier_value: XX-XX-XXX-M-RMM
- identifier_scheme: GHCID_UUID
identifier_value: ee2fc2a8-6b81-5af6-8403-81f2d1b94c44
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 22a5b0df-8029-8ca5-9998-9fcfa97142c5
- identifier_scheme: GHCID_NUMERIC
identifier_value: '2496596042421218469'
- identifier_scheme: RECORD_ID
identifier_value: 2bb2af3b-3a7a-4644-b199-f3037e0bd086
- *id001
- *id002
- *id003
- *id004
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T11:35:45.745306+00:00'
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
confidence_score: 0.85
notes:
- 'Country resolved 2025-12-06T23:54:39Z: XX→CZ via Wikidata P17'
- 'Location resolved 2025-12-07T00:19:31Z: CH-Annotator TOP.SET extraction ''Mělník''
-> Melnik (GeoNames:3070862, Region:72)'
ch_annotator:
convention_id: ch_annotator-v1_7_0
convention_version: 1.7.0
entity_classification:
hypernym: GRP
hypernym_label: GROUP
subtype: GRP.HER.MUS
subtype_label: MUSEUM
ontology_class: schema:Museum
alternative_classes:
- org:FormalOrganization
- rov:RegisteredOrganization
- glam:HeritageCustodian
extraction_provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.745306+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
annotation_provenance:
annotation_agent: opencode-claude-sonnet-4
annotation_date: '2025-12-06T21:12:32.389491+00:00'
annotation_method: retroactive CH-Annotator application via batch script
source_file: czech_unified.yaml
annotation_metadata:
confidence_score: 0.85
verified: false
verification_date: null
verified_by: null
entity_claims:
- claim_type: full_name
claim_value: Regionální muzeum Mělník
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.745306+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.85
- claim_type: institution_type
claim_value: MUSEUM
property_uri: rdf:type
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.745306+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: wikidata_id
claim_value: Q12049106
property_uri: owl:sameAs
provenance:
namespace: wikidata
path: /entity/Q12049106
timestamp: '2025-11-19T11:35:45.745306+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.98
- claim_type: location_settlement
claim_value: Melnik
property_uri: schema:location
hypernym_code: TOP.SET
hypernym_label: SETTLEMENT
provenance:
namespace: geonames
path: /geonames/3070862
timestamp: '2025-12-07T00:19:31.882227+00:00'
agent: extract_locations_ch_annotator.py
context_convention: ch_annotator-v1_7_0
confidence: 0.85
extraction_source:
field: institution_name
extracted_text: Mělník
method: pattern_matching
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:44.730969+00:00'
creation_method: create_custodian_from_ch_annotator.py
wikidata_enrichment:
wikidata_entity_id: Q12049106
wikidata_label_en: Regionální muzeum Mělník