glam/data/custodian/CZ-41-KAV-A-SOAKV.yaml
kempersc 717ee3408a Logo enrichment batch: JP+771, CZ+380 - 10,913 files (34%)
- JP: 2,846 processed (24% of 12,096)
- CZ: 2,550 processed (30% of 8,432)
- CH, NL, BE, AT, BR: 100% complete
- Total: 10,913 of 31,772 files (34%)
- Using crawl4ai favicon extraction
2025-12-25 13:44:26 +01:00

287 lines
9.6 KiB
YAML

custodian_name:
claim_type: custodian_name
claim_value: Státní okresní archiv Karlovy Vary
source_type: ch_annotator
original_entry:
name: Státní okresní archiv Karlovy Vary
institution_type: ARCHIVE
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: ARON_UUID
identifier_value: c6df7070-79ea-4d7f-966b-b5dad37a932c
identifier_url: https://portal.nacr.cz/aron/apu/c6df7070-79ea-4d7f-966b-b5dad37a932c
- &id002
identifier_scheme: INSTITUTION_CODE
identifier_value: '223202010'
- &id003
identifier_scheme: Wikidata
identifier_value: Q54008623
identifier_url: https://www.wikidata.org/wiki/Q54008623
- &id004
identifier_scheme: VIAF
identifier_value: '145237882'
identifier_url: https://viaf.org/viaf/145237882
locations: []
processing_timestamp: '2025-12-06T23:37:44.665611+00:00'
ghcid:
ghcid_current: CZ-41-KAV-A-SOAKV
ghcid_original: XX-XX-XXX-A-SOAKV
ghcid_uuid: 79fa747a-a895-5fee-9ffa-b3081682e617
ghcid_uuid_sha256: c6282245-0241-8878-3580-b04bbcb7ae7a
ghcid_numeric: 14278700298364119160
record_id: 1e9bcbb9-79b6-466f-9de4-0a7fd8318961
generation_timestamp: '2025-12-06T23:37:44.665611+00:00'
location_resolution:
country_code: CZ
region_code: '41'
city_code: KAV
method: CH_ANNOTATOR_TOP_SET
resolution_timestamp: '2025-12-07T00:20:05.508064+00:00'
region_name: CZ-41
iso_code_source: CZ-41
city_name: Karlovy Vary
geonames_id: 3073803
feature_code: PPLA
extracted_toponym: Karlovy
latitude: 50.23271
longitude: 12.87117
ghcid_history:
- previous_ghcid_component: KV
new_ghcid_component: KAV
change_date: '2025-12-20T19:57:18Z'
reason: 'Fixed 2-letter city code to proper 3-letter code per AGENTS.md. City:
Karlovy Vary'
- ghcid: XX-XX-XXX-A-SOAKV
ghcid_numeric: 14278700298364119160
valid_from: '2025-12-06T23:37:44.665611+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
- ghcid: CZ-XX-XXX-A-SOAKV
valid_from: '2025-12-06T23:54:39.168997+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-41-XXX-A-SOAKV
valid_from: '2025-12-07T00:02:04.200317+00:00'
reason: 'Region resolved via Wikidata P131: XX->41 (CZ-41)'
- ghcid: CZ-41-KV-A-SOAKV
valid_from: '2025-12-07T00:20:05.508072+00:00'
reason: 'Location resolved via CH-Annotator TOP.SET extraction: Karlovy -> Karlovy
Vary (GeoNames:3073803)'
identifiers:
- identifier_scheme: GHCID
identifier_value: XX-XX-XXX-A-SOAKV
- identifier_scheme: GHCID_UUID
identifier_value: 79fa747a-a895-5fee-9ffa-b3081682e617
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: c6282245-0241-8878-3580-b04bbcb7ae7a
- identifier_scheme: GHCID_NUMERIC
identifier_value: '14278700298364119160'
- identifier_scheme: RECORD_ID
identifier_value: 1e9bcbb9-79b6-466f-9de4-0a7fd8318961
- *id001
- *id002
- *id003
- *id004
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T11:35:45.745184+00:00'
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
confidence_score: 0.85
notes:
- 'Country resolved 2025-12-06T23:54:39Z: XX→CZ via Wikidata P17'
- 'Region resolved 2025-12-07T00:02:04Z: XX->41 via Wikidata P131 (CZ-41)'
- 'Location resolved 2025-12-07T00:20:05Z: CH-Annotator TOP.SET extraction ''Karlovy''
-> Karlovy Vary (GeoNames:3073803, Region:41)'
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:12Z
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:35Z
- 'YouTube/Google Maps enrichment 2025-12-09T09:31:06Z: 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.ARC
subtype_label: ARCHIVE
ontology_class: schema:ArchiveOrganization
alternative_classes:
- org:FormalOrganization
- rov:RegisteredOrganization
- glam:HeritageCustodian
extraction_provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.745184+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: Státní okresní archiv Karlovy Vary
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.745184+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.85
- claim_type: institution_type
claim_value: ARCHIVE
property_uri: rdf:type
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.745184+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: wikidata_id
claim_value: Q54008623
property_uri: owl:sameAs
provenance:
namespace: wikidata
path: /entity/Q54008623
timestamp: '2025-11-19T11:35:45.745184+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.98
- claim_type: location_settlement
claim_value: Karlovy Vary
property_uri: schema:location
hypernym_code: TOP.SET
hypernym_label: SETTLEMENT
provenance:
namespace: geonames
path: /geonames/3073803
timestamp: '2025-12-07T00:20:05.508075+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: Karlovy
method: pattern_matching
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:44.665611+00:00'
creation_method: create_custodian_from_ch_annotator.py
wikidata_enrichment:
wikidata_entity_id: Q54008623
api_metadata:
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
fetch_timestamp: '2025-12-08T23:43:31.271066+00:00'
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
enrichment_version: 2.0_full
properties_found:
- P31
- P17
- P361
- P214
- P159
- P856
- P213
- P244
- P18
- P131
- P571
- P625
- P373
- P2671
wikidata_labels:
cs: Státní okresní archiv Karlovy Vary
en: Státní okresní archiv Karlovy Vary
wikidata_label_en: Státní okresní archiv Karlovy Vary
wikidata_descriptions:
cs: archiv v Karlových Varech
wikidata_aliases:
cs:
- SOkA Karlovy Vary
wikidata_sitelinks:
cswiki: Státní okresní archiv Karlovy Vary
commonswiki: Category:Státní okresní archiv Karlovy Vary
wikidata_temporal:
inception: '1954-00-00'
wikidata_inception: '1954-00-00'
wikidata_classification:
instance_of: &id005
- id: Q53131316
label: state district archive
description: Archive type in the Czech Republic
wikidata_instance_of: *id005
wikidata_location:
country: &id007
id: Q213
label: Czech Republic
description: country in Central Europe
headquarters_location: &id006
id: Q384544
label: Karlovy Vary
description: city in Karlovy Vary Region, Czechia
located_in_admin_entity: *id006
coordinates: &id008
latitude: 50.2343103
longitude: 12.8532978
precision: 1.0e-07
wikidata_country: *id007
wikidata_located_in: *id006
wikidata_coordinates: *id008
wikidata_organization:
part_of:
id: Q21953079
label: State Regional Archives in Pilsen
description: archive covering West Bohemia, Czechia
wikidata_web:
official_website: http://www.soaplzen.cz/soka-kv
wikidata_official_website: http://www.soaplzen.cz/soka-kv
wikidata_media:
image: Karlovy Vary Státní okresní archiv 2.jpg
commons_category: Státní okresní archiv Karlovy Vary
wikidata_image: Karlovy Vary Státní okresní archiv 2.jpg
location:
latitude: 50.2343103
longitude: 12.8532978
coordinate_provenance:
source_type: WIKIDATA
source_path: wikidata_enrichment.wikidata_coordinates
original_timestamp: '2025-12-08T23:43:31.271066+00:00'
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
entity_id: Q54008623
city: Karlovy Vary
region: CZ-41
region_code: '41'
country: CZ
geonames_id: 3073803
feature_code: PPLA
normalization_timestamp: '2025-12-09T06:49:35.042326+00:00'
youtube_status: NOT_FOUND
youtube_search_query: Státní okresní archiv Karlovy Vary official
youtube_search_timestamp: '2025-12-09T09:31:06.515441+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-24T12:02:53.885625+00:00'
source_url: http://www.soaplzen.cz/soka-kv
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://www.soaplzen.cz/sites/default/files/easybreeze_favicon.ico
source_url: http://www.soaplzen.cz/soka-kv
css_selector: '[document] > html.js > head > link'
retrieved_on: '2025-12-24T12:02:53.885625+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: image/x-icon
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 1