f284e87d13
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
142 lines
4.8 KiB
YAML
142 lines
4.8 KiB
YAML
original_entry:
|
|
name: Muzeum Aš
|
|
institution_type: MUSEUM
|
|
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: ARON_UUID
|
|
identifier_value: b3faa61d-df60-4b7d-a34e-43e7e1fc1cda
|
|
identifier_url: https://portal.nacr.cz/aron/apu/b3faa61d-df60-4b7d-a34e-43e7e1fc1cda
|
|
- &id002
|
|
identifier_scheme: INSTITUTION_CODE
|
|
identifier_value: '903201010'
|
|
locations: []
|
|
processing_timestamp: '2025-12-06T23:37:44.577325+00:00'
|
|
ghcid:
|
|
ghcid_current: CZ-41-AS-M-MA
|
|
ghcid_original: XX-XX-XXX-M-MA
|
|
ghcid_uuid: b0f0382c-5e9d-544d-a21b-fde2aeb661fb
|
|
ghcid_uuid_sha256: a1636922-f140-82da-5992-8900117f0b3e
|
|
ghcid_numeric: 11629254261598069466
|
|
record_id: 74becec7-e867-4be8-be75-1bbeaf788aef
|
|
generation_timestamp: '2025-12-06T23:37:44.577325+00:00'
|
|
location_resolution:
|
|
country_code: CZ
|
|
region_code: '41'
|
|
city_code: AS
|
|
method: CH_ANNOTATOR_TOP_SET
|
|
resolution_timestamp: '2025-12-07T00:19:29.890706+00:00'
|
|
city_name: As
|
|
geonames_id: 3079751
|
|
feature_code: PPL
|
|
extracted_toponym: Aš
|
|
latitude: 50.22387
|
|
longitude: 12.19499
|
|
ghcid_history:
|
|
- ghcid: XX-XX-XXX-M-MA
|
|
ghcid_numeric: 11629254261598069466
|
|
valid_from: '2025-12-06T23:37:44.577325+00:00'
|
|
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
- ghcid: CZ-XX-XXX-M-MA
|
|
valid_from: '2025-12-06T23:56:13.577640+00:00'
|
|
reason: 'Country resolved via Wikidata P17: XX→CZ'
|
|
- ghcid: CZ-41-AS-M-MA
|
|
valid_from: '2025-12-07T00:19:29.890715+00:00'
|
|
reason: 'Location resolved via CH-Annotator TOP.SET extraction: Aš -> As (GeoNames:3079751)'
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: Muzeum Aš
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: XX-XX-XXX-M-MA
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: b0f0382c-5e9d-544d-a21b-fde2aeb661fb
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: a1636922-f140-82da-5992-8900117f0b3e
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '11629254261598069466'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 74becec7-e867-4be8-be75-1bbeaf788aef
|
|
- *id001
|
|
- *id002
|
|
provenance:
|
|
data_source: API_SCRAPING
|
|
data_tier: TIER_1_AUTHORITATIVE
|
|
extraction_date: '2025-11-19T11:35:45.745026+00:00'
|
|
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
|
|
confidence_score: 0.85
|
|
notes:
|
|
- 'Country resolved 2025-12-06T23:56:13Z: XX→CZ via Wikidata P17'
|
|
- 'Location resolved 2025-12-07T00:19:29Z: CH-Annotator TOP.SET extraction ''Aš''
|
|
-> As (GeoNames:3079751, Region:41)'
|
|
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: '2025-11-19T11:35:45.745026+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: Muzeum Aš
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T11:35:45.745026+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: '2025-11-19T11:35:45.745026+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: location_settlement
|
|
claim_value: As
|
|
property_uri: schema:location
|
|
hypernym_code: TOP.SET
|
|
hypernym_label: SETTLEMENT
|
|
provenance:
|
|
namespace: geonames
|
|
path: /geonames/3079751
|
|
timestamp: '2025-12-07T00:19:29.890718+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: Aš
|
|
method: pattern_matching
|
|
integration_note:
|
|
created_from: czech_unified_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:37:44.577325+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|