57de5e4b11
- Added logo_enrichment to 771 Czech custodian files - 87% logo hit rate using crawl4ai favicon extraction - Total checkpoint: 9,257 files across all countries - CZ remaining: 6,642 files
208 lines
6.8 KiB
YAML
208 lines
6.8 KiB
YAML
original_entry:
|
|
name: Knihovna Jiřiny Šiklové
|
|
institution_type: LIBRARY
|
|
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: Sigla
|
|
identifier_value: ABE190
|
|
- &id002
|
|
identifier_scheme: IČO
|
|
identifier_value: '25737058'
|
|
- &id003
|
|
identifier_scheme: DIČ
|
|
identifier_value: CZ25737058
|
|
- &id004
|
|
identifier_scheme: Website
|
|
identifier_value: https://genderstudies.tritius.cz/
|
|
identifier_url: https://genderstudies.tritius.cz/
|
|
locations:
|
|
- street_address: Masarykovo nábřeží 8
|
|
postal_code: 120 00
|
|
city: Praha 2
|
|
region: Hlavní město Praha
|
|
country: CZ
|
|
latitude: 50.076972
|
|
longitude: 14.414558
|
|
processing_timestamp: '2025-12-06T23:37:19.382744+00:00'
|
|
ghcid:
|
|
ghcid_current: CZ-10-PRA-L-KJS
|
|
ghcid_original: CZ-HL-PRA-L-KJŠ
|
|
ghcid_uuid: 0389c1e8-450c-5e38-97af-13e72964ee3c
|
|
ghcid_uuid_sha256: 1aa61138-78a9-840e-90aa-49a28852a11d
|
|
ghcid_numeric: 1920241225360339982
|
|
record_id: 1d9c2e65-232b-4922-be14-8cde41eebb8e
|
|
generation_timestamp: '2025-12-06T23:37:19.382744+00:00'
|
|
location_resolution:
|
|
country_code: CZ
|
|
region_code: 10
|
|
city_code: PRA
|
|
method: CH_ANNOTATOR_SOURCE
|
|
ghcid_history:
|
|
- ghcid: CZ-10-PRA-L-KJS
|
|
valid_from: '2025-12-10T09:46:58Z'
|
|
valid_to: null
|
|
reason: Corrected region code from CZ-HL to CZ-10 (Prague (Hlavní město Praha))
|
|
per ISO 3166-2:CZ
|
|
- ghcid: CZ-HL-PRA-L-KJS
|
|
valid_from: null
|
|
valid_to: '2025-12-10T09:46:58Z'
|
|
reason: Previous GHCID with incorrect region code
|
|
- ghcid: CZ-HL-PRA-L-KJS
|
|
ghcid_numeric: 1920241225360339982
|
|
valid_from: '2025-12-08T11:21:39.000640+00:00'
|
|
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-HL-PRA-L-KJŠ)'
|
|
- ghcid: CZ-HL-PRA-L-KJŠ
|
|
ghcid_numeric: 131701892371590362
|
|
valid_from: '2025-12-06T23:37:19.382744+00:00'
|
|
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
valid_to: '2025-12-08T11:21:39.000640+00:00'
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: Knihovna Jiřiny Šiklové
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: CZ-10-PRA-L-KJS
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 0389c1e8-450c-5e38-97af-13e72964ee3c
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 1aa61138-78a9-840e-90aa-49a28852a11d
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '1920241225360339982'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 1d9c2e65-232b-4922-be14-8cde41eebb8e
|
|
- *id001
|
|
- *id002
|
|
- *id003
|
|
- *id004
|
|
- identifier_scheme: Wikidata
|
|
identifier_value: Q114618342
|
|
identifier_url: https://www.wikidata.org/wiki/Q114618342
|
|
provenance:
|
|
data_source: API_SCRAPING
|
|
data_tier: TIER_1_AUTHORITATIVE
|
|
extraction_date: '2025-11-19T10:14:29.963299+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 2025-12-08T23:11:48Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:49:16Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:50:51Z
|
|
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: '2025-11-19T10:14:29.963299+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: Knihovna Jiřiny Šiklové
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:29.963299+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: '2025-11-19T10:14:29.963299+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: '2025-11-19T10:14:29.963299+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.9
|
|
- claim_type: ghcid
|
|
claim_value: CZ-ABE190
|
|
property_uri: glam:ghcid
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:29.963299+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: '2025-12-06T23:37:19.382744+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
location:
|
|
latitude: 50.076972
|
|
longitude: 14.414558
|
|
coordinate_provenance:
|
|
source_type: ORIGINAL_ENTRY
|
|
source_path: original_entry.locations[0]
|
|
city: Praha 2
|
|
region: Hlavní město Praha
|
|
region_code: 10
|
|
country: CZ
|
|
postal_code: 120 00
|
|
street_address: Masarykovo nábřeží 8
|
|
normalization_timestamp: '2025-12-09T06:50:51.693471+00:00'
|
|
wikidata_enrichment:
|
|
wikidata_id: Q114618342
|
|
wikidata_url: https://www.wikidata.org/wiki/Q114618342
|
|
matched_by: sigla_identifier
|
|
matched_sigla: ABE190
|
|
wikidata_label: Gender Studies, o.p.s., knihovna
|
|
wikidata_description: knihovna v Praze
|
|
enrichment_date: '2025-12-19T10:13:14.698084+00:00'
|
|
enrichment_version: 2.1.0
|
|
instance_of:
|
|
- Q385994
|
|
logo_enrichment:
|
|
enrichment_timestamp: '2025-12-23T22:11:40.322006+00:00'
|
|
source_url: https://genderstudies.tritius.cz
|
|
extraction_method: crawl4ai
|
|
claims:
|
|
- claim_type: favicon_url
|
|
claim_value: https://genderstudies.tritius.cz/apple-touch-icon-180x180.png
|
|
source_url: https://genderstudies.tritius.cz
|
|
css_selector: '[document] > html > head > link:nth-of-type(14)'
|
|
retrieved_on: '2025-12-23T22:11:40.322006+00:00'
|
|
extraction_method: crawl4ai_link_rel
|
|
favicon_type: ''
|
|
favicon_sizes: 180x180
|
|
summary:
|
|
total_claims: 1
|
|
has_primary_logo: false
|
|
has_favicon: true
|
|
has_og_image: false
|
|
favicon_count: 14
|