glam/data/custodian.backup.20251230/CZ-80-VSE-A-SOAV.yaml
2025-12-30 23:19:38 +01:00

261 lines
8.8 KiB
YAML

original_entry:
name: Státní okresní archiv Vsetín
institution_type: ARCHIVE
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: ARON_UUID
identifier_value: 014b13b9-7011-4d7b-902c-c5323b6bae62
identifier_url: https://portal.nacr.cz/aron/apu/014b13b9-7011-4d7b-902c-c5323b6bae62
- &id002
identifier_scheme: INSTITUTION_CODE
identifier_value: '226303010'
- &id003
identifier_scheme: Wikidata
identifier_value: Q54314116
identifier_url: https://www.wikidata.org/wiki/Q54314116
- &id004
identifier_scheme: VIAF
identifier_value: '146463443'
identifier_url: https://viaf.org/viaf/146463443
locations: []
processing_timestamp: '2025-12-06T23:37:43.700206+00:00'
ghcid:
ghcid_current: CZ-80-VSE-A-SOAV
ghcid_original: XX-XX-XXX-A-SOAV
ghcid_uuid: 27edc6c4-0872-5de4-9dd2-ac4405469a44
ghcid_uuid_sha256: 26844b96-1c75-804b-a26e-020376f4e01d
ghcid_numeric: 2775426378461691979
record_id: 5b277f7a-17b7-4a06-820c-e85e15ca78c0
generation_timestamp: '2025-12-06T23:37:43.700206+00:00'
location_resolution:
country_code: CZ
region_code: '90'
city_code: VSE
method: CH_ANNOTATOR_TOP_SET
resolution_timestamp: '2025-12-07T00:19:30.743770+00:00'
city_name: Vsetin
geonames_id: 3062339
feature_code: PPL
extracted_toponym: Vsetín
latitude: 49.33871
longitude: 17.99619
ghcid_history:
- ghcid: CZ-80-VSE-A-SOAV
valid_from: '2025-12-10T09:46:57Z'
valid_to:
reason: Corrected region code from CZ-90 to CZ-80 (Moravian-Silesian (Moravskoslezský)) per ISO 3166-2:CZ
- ghcid: CZ-90-VSE-A-SOAV
valid_from:
valid_to: '2025-12-10T09:46:57Z'
reason: Previous GHCID with incorrect region code
- ghcid: XX-XX-XXX-A-SOAV
ghcid_numeric: 2775426378461691979
valid_from: '2025-12-06T23:37:43.700206+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
- ghcid: CZ-XX-XXX-A-SOAV
valid_from: '2025-12-06T23:54:38.775959+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-90-VSE-A-SOAV
valid_from: '2025-12-07T00:19:30.743779+00:00'
reason: 'Location resolved via CH-Annotator TOP.SET extraction: Vsetín -> Vsetin (GeoNames:3062339)'
custodian_name:
claim_type: custodian_name
claim_value: Státní okresní archiv Vsetín
source_type: ch_annotator
identifiers:
- identifier_scheme: GHCID
identifier_value: XX-XX-XXX-A-SOAV
- identifier_scheme: GHCID_UUID
identifier_value: 27edc6c4-0872-5de4-9dd2-ac4405469a44
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 26844b96-1c75-804b-a26e-020376f4e01d
- identifier_scheme: GHCID_NUMERIC
identifier_value: '2775426378461691979'
- identifier_scheme: RECORD_ID
identifier_value: 5b277f7a-17b7-4a06-820c-e85e15ca78c0
- *id001
- *id002
- *id003
- *id004
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T11:35:45.743213+00:00'
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
confidence_score: 0.85
notes:
- 'Country resolved 2025-12-06T23:54:38Z: XX→CZ via Wikidata P17'
- 'Location resolved 2025-12-07T00:19:30Z: CH-Annotator TOP.SET extraction ''Vsetín'' -> Vsetin (GeoNames:3062339, Region:90)'
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:11:46Z
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:49:10Z
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:50:45Z
schema_version: 2.0.0
enrichment_provenance:
wikidata_enrichment:
content_hash: sha256-LcOesmB0WbKW5NiYWPXDYfKEKGhvKHC4MxJrOLPvVOY=
verified_at: '2025-12-28T20:00:56.347199+00:00'
wasDerivedFrom: https://www.wikidata.org/wiki/Q54314116
provenance_schema_version: '2.0'
standards_compliance:
- W3C PROV-O
- W3C SRI (content hashes)
generated_at: '2025-12-28T20:00:56.347219+00:00'
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: '2025-11-19T11:35:45.743213+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:
verified_by:
entity_claims:
- claim_type: full_name
claim_value: Státní okresní archiv Vsetín
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.743213+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: '2025-11-19T11:35:45.743213+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: wikidata_id
claim_value: Q54314116
property_uri: owl:sameAs
provenance:
namespace: wikidata
path: /entity/Q54314116
timestamp: '2025-11-19T11:35:45.743213+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.98
- claim_type: location_settlement
claim_value: Vsetin
property_uri: schema:location
hypernym_code: TOP.SET
hypernym_label: SETTLEMENT
provenance:
namespace: geonames
path: /geonames/3062339
timestamp: '2025-12-07T00:19:30.743782+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: Vsetín
method: pattern_matching
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:43.700206+00:00'
creation_method: create_custodian_from_ch_annotator.py
wikidata_enrichment:
wikidata_entity_id: Q54314116
api_metadata:
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
fetch_timestamp: '2025-12-18T23:57:59.801376+00:00'
user_agent: GLAMDataExtractor/1.2 (glam-data@example.com) Python/httpx
enrichment_version: 2.1_generic
properties_found:
- P31
- P361
- P856
- P214
- P159
- P17
wikidata_labels:
cs: Státní okresní archiv Vsetín
en: State District Archives Vsetín
wikidata_label_en: State District Archives Vsetín
wikidata_label_cs: Státní okresní archiv Vsetín
wikidata_descriptions:
cs: archiv ve Vsetíně
wikidata_aliases:
cs:
- SOkA Vsetín
wikidata_classification:
instance_of: &id005
- id: Q53131316
label: state district archive
description: Archive type in the Czech Republic
wikidata_instance_of: *id005
wikidata_location:
headquarters_location:
id: Q513417
label: Vsetín
description: town in the Zlín Region in Czechia
country: &id006
id: Q213
label: Czech Republic
description: country in Central Europe
wikidata_country: *id006
wikidata_organization:
part_of:
id: Q12038677
label: Moravian regional archive
description: česká výzkumná organizace
wikidata_web:
official_website: http://vsetin.mza.cz/
wikidata_official_website: http://vsetin.mza.cz/
_provenance:
content_hash:
algorithm: sha256
value: sha256-LcOesmB0WbKW5NiYWPXDYfKEKGhvKHC4MxJrOLPvVOY=
scope: enrichment_section
computed_at: '2025-12-28T20:00:56.347199+00:00'
prov:
wasGeneratedBy:
'@type': prov:Activity
name: wikidata_api_fetch
used: https://www.wikidata.org/w/rest.php/wikibase/v1
wasDerivedFrom: https://www.wikidata.org/wiki/Q54314116
verification:
status: verified
last_verified: '2025-12-28T20:00:56.347209+00:00'
location:
latitude: 49.33871
longitude: 17.99619
coordinate_provenance:
source_type: GHCID_RESOLUTION_DIRECT
source_path: ghcid.location_resolution
original_timestamp: '2025-12-07T00:19:30.743770+00:00'
entity_id: 3062339
resolution_method: CH_ANNOTATOR_TOP_SET
city: Vsetin
region_code: '90'
country: CZ
geonames_id: 3062339
feature_code: PPL
normalization_timestamp: '2025-12-09T06:50:45.410296+00:00'