glam/data/custodian/CZ-71-SUM-A-SOAS.yaml
2025-12-30 23:01:01 +01:00

295 lines
10 KiB
YAML

original_entry:
name: Státní okresní archiv Šumperk
institution_type: ARCHIVE
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: ARON_UUID
identifier_value: 6683aa94-18c4-4fe4-8b81-81397bc85a5f
identifier_url: https://portal.nacr.cz/aron/apu/6683aa94-18c4-4fe4-8b81-81397bc85a5f
- &id002
identifier_scheme: INSTITUTION_CODE
identifier_value: '227105010'
- &id003
identifier_scheme: Wikidata
identifier_value: Q54800389
identifier_url: https://www.wikidata.org/wiki/Q54800389
- &id004
identifier_scheme: VIAF
identifier_value: '154658705'
identifier_url: https://viaf.org/viaf/154658705
locations: []
processing_timestamp: '2025-12-06T23:37:44.230629+00:00'
ghcid:
ghcid_current: CZ-71-SUM-A-SOAS
ghcid_original: XX-XX-XXX-A-SOAŠ
ghcid_uuid: 12e78474-dd12-56a9-9cbc-a0b61a5379f0
ghcid_uuid_sha256: 8d53a013-5d0f-82ef-9e01-6dc6fab9324a
ghcid_numeric: 10183659187440964335
record_id: f9393a33-ae92-4142-9a45-02bbb0a1ec75
generation_timestamp: '2025-12-06T23:37:44.230629+00:00'
location_resolution:
country_code: CZ
region_code: '71'
city_code: SUM
method: CH_ANNOTATOR_TOP_SET
resolution_timestamp: '2025-12-07T00:20:05.378527+00:00'
region_name: CZ-71
iso_code_source: CZ-71
city_name: Sumperk
geonames_id: 3064673
feature_code: PPL
extracted_toponym: Šumperk
latitude: 49.96528
longitude: 16.97061
ghcid_history:
- ghcid: CZ-71-SUM-A-SOAS
ghcid_numeric: 10183659187440964335
valid_from: '2025-12-08T11:21:32.847248+00:00'
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-71-SUM-A-SOAŠ)'
- ghcid: XX-XX-XXX-A-SOAŠ
ghcid_numeric: 5046094704919204578
valid_from: '2025-12-06T23:37:44.230629+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
valid_to: '2025-12-08T11:21:32.847248+00:00'
- ghcid: CZ-XX-XXX-A-SOAŠ
valid_from: '2025-12-06T23:54:38.380179+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-71-XXX-A-SOAŠ
valid_from: '2025-12-07T00:00:37.481660+00:00'
reason: 'Region resolved via Wikidata P131: XX->71 (CZ-71)'
- ghcid: CZ-71-SUM-A-SOAŠ
valid_from: '2025-12-07T00:20:05.378534+00:00'
reason: 'Location resolved via CH-Annotator TOP.SET extraction: Šumperk -> Sumperk (GeoNames:3064673)'
custodian_name:
claim_type: custodian_name
claim_value: Státní okresní archiv Šumperk
source_type: ch_annotator
identifiers:
- identifier_scheme: GHCID
identifier_value: CZ-71-SUM-A-SOAS
- identifier_scheme: GHCID_UUID
identifier_value: 12e78474-dd12-56a9-9cbc-a0b61a5379f0
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 8d53a013-5d0f-82ef-9e01-6dc6fab9324a
- identifier_scheme: GHCID_NUMERIC
identifier_value: '10183659187440964335'
- identifier_scheme: RECORD_ID
identifier_value: f9393a33-ae92-4142-9a45-02bbb0a1ec75
- *id001
- *id002
- *id003
- *id004
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T11:35:45.744311+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'
- 'Region resolved 2025-12-07T00:00:37Z: XX->71 via Wikidata P131 (CZ-71)'
- 'Location resolved 2025-12-07T00:20:05Z: CH-Annotator TOP.SET extraction ''Šumperk'' -> Sumperk (GeoNames:3064673, Region:52)'
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:50Z
- 'YouTube/Google Maps enrichment 2025-12-09T09:35:50Z: YouTube: not found'
schema_version: 2.0.0
enrichment_provenance:
wikidata_enrichment:
content_hash: sha256-zmlPgGgbFvvIo9nPZ6dJWZ+F0Q1e6cteSssHERughZo=
verified_at: '2025-12-28T20:00:08.291207+00:00'
wasDerivedFrom: https://www.wikidata.org/wiki/Q54800389
provenance_schema_version: '2.0'
standards_compliance:
- W3C PROV-O
- W3C SRI (content hashes)
generated_at: '2025-12-28T20:00:08.291224+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
agent: batch-script-create-custodian-from-ch-annotator
context_convention: ch_annotator-v1_7_0
source_archived_at: '2025-11-19T11:35:45.744311+00:00'
statement_created_at: '2025-12-06T21:12:32.389491+00:00'
source_type: library_registry_api
migration_note: Migrated from agent:claude-conversation on 2025-12-30
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 Šumperk
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/czech_unified.yaml
agent: batch-script-create-custodian-from-ch-annotator
context_convention: ch_annotator-v1_7_0
source_archived_at: '2025-11-19T11:35:45.744311+00:00'
statement_created_at: '2025-12-06T21:12:32.389491+00:00'
source_type: library_registry_api
migration_note: Migrated from agent:claude-conversation on 2025-12-30
confidence: 0.85
- claim_type: institution_type
claim_value: ARCHIVE
property_uri: rdf:type
provenance:
namespace: glam
path: /files/czech_unified.yaml
agent: batch-script-create-custodian-from-ch-annotator
context_convention: ch_annotator-v1_7_0
source_archived_at: '2025-11-19T11:35:45.744311+00:00'
statement_created_at: '2025-12-06T21:12:32.389491+00:00'
source_type: library_registry_api
migration_note: Migrated from agent:claude-conversation on 2025-12-30
confidence: 0.95
- claim_type: wikidata_id
claim_value: Q54800389
property_uri: owl:sameAs
provenance:
namespace: wikidata
path: /entity/Q54800389
agent: batch-script-create-custodian-from-ch-annotator
context_convention: ch_annotator-v1_7_0
source_archived_at: '2025-11-19T11:35:45.744311+00:00'
statement_created_at: '2025-12-06T21:12:32.389491+00:00'
source_type: library_registry_api
migration_note: Migrated from agent:claude-conversation on 2025-12-30
confidence: 0.98
- claim_type: location_settlement
claim_value: Sumperk
property_uri: schema:location
hypernym_code: TOP.SET
hypernym_label: SETTLEMENT
provenance:
namespace: geonames
path: /geonames/3064673
timestamp: '2025-12-07T00:20:05.378537+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: Šumperk
method: pattern_matching
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:44.230629+00:00'
creation_method: create_custodian_from_ch_annotator.py
wikidata_enrichment:
wikidata_entity_id: Q54800389
api_metadata:
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
fetch_timestamp: '2025-12-08T23:48:28.052411+00:00'
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
enrichment_version: 2.0_full
properties_found:
- P31
- P17
- P361
- P856
- P214
- P159
wikidata_labels:
cs: Státní okresní archiv Šumperk
wikidata_descriptions:
cs: archiv v Šumperku
wikidata_aliases:
cs:
- SOkA Šumperk
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: &id006
id: Q213
label: Czech Republic
description: country in Central Europe
headquarters_location:
id: Q392692
label: Šumperk
description: town in Czechia
wikidata_country: *id006
wikidata_organization:
part_of:
id: Q10860553
label: Regional Archives in Opava
description: Czech state regional archive
wikidata_web:
official_website: http://www.archives.cz/web/soka/sumperk/o_archivu/
wikidata_official_website: http://www.archives.cz/web/soka/sumperk/o_archivu/
_provenance:
content_hash:
algorithm: sha256
value: sha256-zmlPgGgbFvvIo9nPZ6dJWZ+F0Q1e6cteSssHERughZo=
scope: enrichment_section
computed_at: '2025-12-28T20:00:08.291207+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/Q54800389
verification:
status: verified
last_verified: '2025-12-28T20:00:08.291215+00:00'
location:
latitude: 49.96528
longitude: 16.97061
coordinate_provenance:
source_type: GHCID_RESOLUTION_DIRECT
source_path: ghcid.location_resolution
original_timestamp: '2025-12-07T00:20:05.378527+00:00'
entity_id: 3064673
resolution_method: CH_ANNOTATOR_TOP_SET
city: Sumperk
region: CZ-71
region_code: '71'
country: CZ
geonames_id: 3064673
feature_code: PPL
normalization_timestamp: '2025-12-09T06:49:50.984387+00:00'
youtube_status: NOT_FOUND
youtube_search_query: Státní okresní archiv Šumperk official
youtube_search_timestamp: '2025-12-09T09:35:50.941663+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-27T22:00:02.369859+00:00'
source_url: http://www.archives.cz/web/soka/sumperk/o_archivu
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.archives.cz/web/favicon/safari-pinned-tab.svg
source_url: http://www.archives.cz/web/soka/sumperk/o_archivu
css_selector: '[document] > html.js.no-touchevents > head > link:nth-of-type(5)'
retrieved_on: '2025-12-27T22:00:02.369859+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 12