2137c522db
- JP: Handle Gun/Cho/Machi/Mura compound city names (2615 files) - CZ: Map city codes to GeoNames entries (667 files) - Overall coverage: 84.5% → 96.4%
166 lines
5.7 KiB
YAML
166 lines
5.7 KiB
YAML
original_entry:
|
|
name: ČSAV - Laboratoř vyšší nervové činnosti
|
|
institution_type: LIBRARY
|
|
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: Sigla
|
|
identifier_value: ABB028
|
|
locations:
|
|
- street_address: Albertov 2
|
|
postal_code: 120 00
|
|
city: Praha 2
|
|
country: CZ
|
|
processing_timestamp: '2025-12-06T23:37:23.644883+00:00'
|
|
ghcid:
|
|
ghcid_current: CZ-10-PRA-L-CLVNC
|
|
ghcid_original: CZ-XX-PRA-L-ČLVNČ
|
|
ghcid_uuid: 7c4e2e3f-7435-5496-8a44-cf18477a95d6
|
|
ghcid_uuid_sha256: 09f9af48-8f3e-8d81-a74f-e6130eb84db5
|
|
ghcid_numeric: 718798341718076801
|
|
record_id: fa90199a-26cd-439c-8c75-aace1ccd0938
|
|
generation_timestamp: '2025-12-06T23:37:23.644883+00:00'
|
|
location_resolution:
|
|
country_code: CZ
|
|
region_code: '10'
|
|
city_code: PRA
|
|
method: GEONAMES_CITY_LOOKUP
|
|
region_name: CZ-10
|
|
geonames_id: 8629195
|
|
resolution_timestamp: '2025-12-07T11:42:56.283286+00:00'
|
|
ghcid_history:
|
|
- ghcid: CZ-10-PRA-L-CLVNC
|
|
ghcid_numeric: 718798341718076801
|
|
valid_from: '2025-12-08T11:21:22.566985+00:00'
|
|
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-10-PRA-L-ČLVNČ)'
|
|
- ghcid: CZ-XX-PRA-L-ČLVNČ
|
|
ghcid_numeric: 8320741941470449304
|
|
valid_from: '2025-12-06T23:37:23.644883+00:00'
|
|
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
valid_to: '2025-12-08T11:21:22.566985+00:00'
|
|
- ghcid: CZ-10-PRA-L-ČLVNČ
|
|
valid_from: '2025-12-07T11:42:56.283297+00:00'
|
|
reason: 'Region resolved via GeoNames city lookup: XX->10 (Praha Klanovice)'
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: ČSAV - Laboratoř vyšší nervové činnosti
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: CZ-10-PRA-L-CLVNC
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 7c4e2e3f-7435-5496-8a44-cf18477a95d6
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 09f9af48-8f3e-8d81-a74f-e6130eb84db5
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '718798341718076801'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: fa90199a-26cd-439c-8c75-aace1ccd0938
|
|
- *id001
|
|
provenance:
|
|
data_source: API_SCRAPING
|
|
data_tier: TIER_1_AUTHORITATIVE
|
|
extraction_date: '2025-11-19T10:14:30.030582+00:00'
|
|
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
|
|
confidence_score: 0.95
|
|
notes:
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:11:19Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:05Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:29Z
|
|
- 'YouTube/Google Maps enrichment 2025-12-09T09:28:29Z: 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: '2025-11-19T10:14:30.030582+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:
|
|
verified_by:
|
|
entity_claims:
|
|
- claim_type: full_name
|
|
claim_value: ČSAV - Laboratoř vyšší nervové činnosti
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:30.030582+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: '2025-11-19T10:14:30.030582+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: located_in_city
|
|
claim_value: Praha 2
|
|
property_uri: schema:addressLocality
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:30.030582+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.9
|
|
- claim_type: ghcid
|
|
claim_value: CZ-ABB028
|
|
property_uri: glam:ghcid
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:30.030582+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 1.0
|
|
integration_note:
|
|
created_from: czech_unified_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:37:23.644883+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
location:
|
|
city: Prague
|
|
region: CZ-10
|
|
region_code: '10'
|
|
country: CZ
|
|
postal_code: 120 00
|
|
street_address: Albertov 2
|
|
geonames_id: 3067696
|
|
normalization_timestamp: '2025-12-09T20:40:59.066354+00:00'
|
|
latitude: 50.08804
|
|
longitude: 14.42076
|
|
geonames_name: Prague
|
|
feature_code: PPLC
|
|
coordinate_provenance:
|
|
source_type: GEONAMES_GHCID_CITY_CODE
|
|
source_path: data/reference/geonames.db
|
|
entity_id: 3067696
|
|
city_code: PRA
|
|
original_timestamp: '2025-12-09T20:40:59.066344+00:00'
|
|
youtube_status: NOT_FOUND
|
|
youtube_search_query: ČSAV - Laboratoř vyšší nervové činnosti official
|
|
youtube_search_timestamp: '2025-12-09T09:28:29.379760+00:00'
|