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

175 lines
6.5 KiB
YAML

original_entry:
name: Akademie věd ČR - Prognostický ústav
institution_type: LIBRARY
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: Sigla
identifier_value: ABB112
locations:
- street_address: Opletalova 19
postal_code: 110 00
city: Praha 1
country: CZ
processing_timestamp: '2025-12-06T23:37:23.658421+00:00'
ghcid:
ghcid_current: CZ-10-PRA-L-AVCPU
ghcid_original: CZ-XX-PRA-L-AVČPÚ
ghcid_uuid: 8bb4e75c-a21b-5838-acb6-5ff445aed08a
ghcid_uuid_sha256: 5de04df0-b47f-8a74-a7f8-a9bb971668b9
ghcid_numeric: 6764492336526219892
record_id: 018d704c-40a7-4314-802e-d1657a6ef48d
generation_timestamp: '2025-12-06T23:37:23.658421+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: '2025-12-07T11:42:55.506888+00:00'
ghcid_history:
- ghcid: CZ-10-PRA-L-AVCPU
ghcid_numeric: 6764492336526219892
valid_from: '2025-12-08T11:21:21.976876+00:00'
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-10-PRA-L-AVČPÚ)'
- ghcid: CZ-XX-PRA-L-AVČPÚ
ghcid_numeric: 4769545273226280928
valid_from: '2025-12-06T23:37:23.658421+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
valid_to: '2025-12-08T11:21:21.976876+00:00'
- ghcid: CZ-10-PRA-L-AVČPÚ
valid_from: '2025-12-07T11:42:55.506915+00:00'
reason: 'Region resolved via GeoNames city lookup: XX->10 (Praha Klanovice)'
custodian_name:
claim_type: custodian_name
claim_value: Akademie věd ČR - Prognostický ústav
source_type: ch_annotator
identifiers:
- identifier_scheme: GHCID
identifier_value: CZ-10-PRA-L-AVCPU
- identifier_scheme: GHCID_UUID
identifier_value: 8bb4e75c-a21b-5838-acb6-5ff445aed08a
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 5de04df0-b47f-8a74-a7f8-a9bb971668b9
- identifier_scheme: GHCID_NUMERIC
identifier_value: '6764492336526219892'
- identifier_scheme: RECORD_ID
identifier_value: 018d704c-40a7-4314-802e-d1657a6ef48d
- *id001
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T10:14:30.030652+00:00'
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
confidence_score: 0.95
notes:
- 'YouTube/Google Maps enrichment 2025-12-08T19:49:37Z: Maps: rejected by LLM; YouTube: not found'
- 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
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: '2025-11-19T10:14:30.030652+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: Akademie věd ČR - Prognostický ústav
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T10:14:30.030652+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: '2025-11-19T10:14:30.030652+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: located_in_city
claim_value: Praha 1
property_uri: schema:addressLocality
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T10:14:30.030652+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.9
- claim_type: ghcid
claim_value: CZ-ABB112
property_uri: glam:ghcid
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T10:14:30.030652+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: '2025-12-06T23:37:23.658421+00:00'
creation_method: create_custodian_from_ch_annotator.py
google_maps_status: NO_MATCH
google_maps_rejected:
candidate_name: Czech Academy of Sciences
rejection_reason: 'NAME MATCH: The source ''Akademie věd ČR - Prognostický ústav'' (Czech Academy of Sciences - Prognostic
Institute) is a specific research institute. The candidate ''Czech Academy of Sciences'' is the parent umbrella organization.
They are not the same institution. TYPE MATCH: The Google Place types ''point_of_interest'' and ''establishment'' do not
match any of the expected types for a heritage institution (e.g., museum, library, gallery). ENTITY TYPE: The candidate
is an umbrella organization for a national academy of sciences and does not function as a heritage institution.'
timestamp: '2025-12-08T19:49:36.877469+00:00'
youtube_status: NOT_FOUND
youtube_search_query: Akademie věd ČR - Prognostický ústav official
youtube_search_timestamp: '2025-12-08T19:49:37.207233+00:00'
location:
city: Prague
region: CZ-10
region_code: '10'
country: CZ
postal_code: 110 00
street_address: Opletalova 19
geonames_id: 3067696
normalization_timestamp: '2025-12-09T20:40:58.679222+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: '2025-12-09T20:40:58.679209+00:00'