glam/data/custodian.backup.20251230/CZ-10-PRA-L-URB.yaml
2025-12-30 23:19:38 +01:00

203 lines
6.9 KiB
YAML

custodian_name:
claim_type: custodian_name
claim_value: Ústav rozvoje biotechnologií
source_type: ch_annotator
original_entry:
name: Ústav rozvoje biotechnologií
institution_type: LIBRARY
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: Sigla
identifier_value: ABE444
locations: []
processing_timestamp: '2025-12-06T23:37:25.751802+00:00'
ghcid:
ghcid_current: CZ-10-PRA-L-URB
ghcid_original: XX-XX-XXX-L-ÚRB
ghcid_uuid: 17928409-28ee-5819-be46-1674bfe5c74a
ghcid_uuid_sha256: 39de561c-8ba0-8eb4-bcc7-5635da204772
ghcid_numeric: 4169864985593286324
record_id: 608e1d73-2221-43f3-9182-6e1e160afe90
generation_timestamp: '2025-12-06T23:37:25.751802+00:00'
location_resolution:
method: GEONAMES_RESEARCH
country_code: CZ
region_code: '10'
region_name: Prague
city_code: PRA
city_name: Prague
geonames_id: 3067696
admin1_code: '52'
resolution_timestamp: '2025-12-07T12:54:27.718742+00:00'
research_date: '2025-12-07'
research_method: GeoNames database + web search verification
ghcid_history:
- ghcid: CZ-10-PRA-L-URB
ghcid_numeric: 4169864985593286324
valid_from: '2025-12-08T11:21:37.581101+00:00'
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-10-PRA-L-ÚRB)'
- ghcid: XX-XX-XXX-L-ÚRB
ghcid_numeric: 11776843013345624602
valid_from: '2025-12-06T23:37:25.751802+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
valid_to: '2025-12-08T11:21:37.581101+00:00'
- ghcid: CZ-XX-XXX-L-ÚRB
valid_from: '2025-12-06T23:56:13.415352+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-10-PRA-L-ÚRB
valid_from: '2025-12-07T12:54:27.718742+00:00'
reason: 'Region resolved via GeoNames research: XX→10, city: Prague (GeoNames
ID: 3067696)'
identifiers:
- identifier_scheme: GHCID
identifier_value: CZ-10-PRA-L-URB
- identifier_scheme: GHCID_UUID
identifier_value: 17928409-28ee-5819-be46-1674bfe5c74a
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 39de561c-8ba0-8eb4-bcc7-5635da204772
- identifier_scheme: GHCID_NUMERIC
identifier_value: '4169864985593286324'
- identifier_scheme: RECORD_ID
identifier_value: 608e1d73-2221-43f3-9182-6e1e160afe90
- *id001
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T10:14:30.047725+00:00'
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
confidence_score: 0.95
notes:
- 'Country resolved 2025-12-06T23:56:13Z: XX→CZ via Wikidata P17'
- 'Region resolved 2025-12-07: XX→CZ-10 (Prague) via GeoNames research'
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:11:20Z
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:07Z
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:30Z
- 'YouTube/Google Maps enrichment 2025-12-09T09:29:05Z: YouTube: not found'
ch_annotator:
convention_id: ch_annotator-v1_7_0
convention_version: 1.7.0
entity_classification:
hypernym: GRP
hypernym_label: GROUP
subtype: GRP.HER.LIB
subtype_label: LIBRARY
ontology_class: schema:Library
alternative_classes:
- org:FormalOrganization
- rov:RegisteredOrganization
- glam:HeritageCustodian
extraction_provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T10:14:30.047725+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: 0.95
verified: false
verification_date: null
verified_by: null
entity_claims:
- claim_type: full_name
claim_value: Ústav rozvoje biotechnologií
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T10:14:30.047725+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: institution_type
claim_value: LIBRARY
property_uri: rdf:type
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T10:14:30.047725+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: ghcid
claim_value: CZ-ABE444
property_uri: glam:ghcid
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T10:14:30.047725+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 1.0
- claim_type: location_city
claim_value: Prague
property_uri: schema:addressLocality
provenance:
namespace: geonames
path: /cities/3067696/name
timestamp: '2025-12-07T12:54:27.718742+00:00'
agent: glm4.6
context_convention: ch_annotator-v1_7_0
confidence: 0.95
resolution_method: GEONAMES_RESEARCH
- claim_type: location_region
claim_value: Prague
property_uri: schema:addressRegion
provenance:
namespace: geonames
path: /cities/3067696/admin1
timestamp: '2025-12-07T12:54:27.718742+00:00'
agent: glm4.6
context_convention: ch_annotator-v1_7_0
confidence: 0.95
resolution_method: GEONAMES_RESEARCH
- claim_type: location_country
claim_value: CZ
property_uri: schema:addressCountry
provenance:
namespace: geonames
path: /cities/3067696/country
timestamp: '2025-12-07T12:54:27.718742+00:00'
agent: glm4.6
context_convention: ch_annotator-v1_7_0
confidence: 0.98
resolution_method: GEONAMES_RESEARCH
- claim_type: geonames_id
claim_value: '3067696'
property_uri: gn:geonamesId
provenance:
namespace: geonames
path: /cities/3067696
timestamp: '2025-12-07T12:54:27.718742+00:00'
agent: glm4.6
context_convention: ch_annotator-v1_7_0
confidence: 0.98
resolution_method: GEONAMES_RESEARCH
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:25.751802+00:00'
creation_method: create_custodian_from_ch_annotator.py
location:
city: Prague
region: Prague
region_code: '10'
country: CZ
geonames_id: 3067696
normalization_timestamp: '2025-12-09T15:34:43.189951+00:00'
latitude: 50.08804
longitude: 14.42076
coordinate_provenance:
source_type: GEONAMES_LOCAL
source_path: data/reference/geonames.db
entity_id: 3067696
original_timestamp: '2025-12-09T15:34:43.189931+00:00'
geonames_name: Prague
feature_code: PPLC
youtube_status: NOT_FOUND
youtube_search_query: Ústav rozvoje biotechnologií official
youtube_search_timestamp: '2025-12-09T09:29:05.027909+00:00'