- JP: Handle Gun/Cho/Machi/Mura compound city names (2615 files) - CZ: Map city codes to GeoNames entries (667 files) - Overall coverage: 84.5% → 96.4%
239 lines
8.6 KiB
YAML
239 lines
8.6 KiB
YAML
original_entry:
|
||
name: Ústřední archiv zeměměřictví a katastru
|
||
institution_type: ARCHIVE
|
||
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
||
identifiers:
|
||
- &id001
|
||
identifier_scheme: ARON_UUID
|
||
identifier_value: f2292710-de60-4486-89b1-9b72c32b9a58
|
||
identifier_url: https://portal.nacr.cz/aron/apu/f2292710-de60-4486-89b1-9b72c32b9a58
|
||
- &id002
|
||
identifier_scheme: INSTITUTION_CODE
|
||
identifier_value: '610000110'
|
||
- &id003
|
||
identifier_scheme: Wikidata
|
||
identifier_value: Q61719003
|
||
identifier_url: https://www.wikidata.org/wiki/Q61719003
|
||
- &id004
|
||
identifier_scheme: VIAF
|
||
identifier_value: '124802389'
|
||
identifier_url: https://viaf.org/viaf/124802389
|
||
locations: []
|
||
processing_timestamp: '2025-12-06T23:37:44.868053+00:00'
|
||
ghcid:
|
||
ghcid_current: CZ-10-PRA-A-UAZK
|
||
ghcid_original: XX-XX-XXX-A-ÚAZK
|
||
ghcid_uuid: 651cc53a-5ead-57c0-b772-2eac68c75974
|
||
ghcid_uuid_sha256: 52e8e5e6-422c-86a2-9859-d56ebafa79bb
|
||
ghcid_numeric: 5974277682822411938
|
||
record_id: 356e9433-489a-42e7-a01c-ce786ae44072
|
||
generation_timestamp: '2025-12-06T23:37:44.868053+00:00'
|
||
location_resolution:
|
||
country_code: CZ
|
||
region_code: 10
|
||
city_code: PRA
|
||
method: WIKIDATA_LOCATION_RESEARCH
|
||
resolution_timestamp: '2025-12-06T23:54:40.402432+00:00'
|
||
resolution_notes: Central Archive of Surveying and Cadastre in Prague, part of ČÚZK
|
||
ghcid_history:
|
||
- ghcid: CZ-10-PRA-A-UAZK
|
||
ghcid_numeric: 5974277682822411938
|
||
valid_from: '2025-12-08T11:21:26.005064+00:00'
|
||
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-10-PRA-A-ÚAZK)'
|
||
- ghcid: XX-XX-XXX-A-ÚAZK
|
||
ghcid_numeric: 4202405953062605303
|
||
valid_from: '2025-12-06T23:37:44.868053+00:00'
|
||
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
||
valid_to: '2025-12-08T11:21:26.005064+00:00'
|
||
- ghcid: CZ-XX-XXX-A-ÚAZK
|
||
valid_from: '2025-12-06T23:54:40.402438+00:00'
|
||
reason: 'Country resolved via Wikidata P17: XX→CZ'
|
||
- ghcid: CZ-10-PRA-A-ÚAZK
|
||
valid_from: '2025-12-07T12:36:58.334618+00:00'
|
||
reason: 'Location resolved via Wikidata research: Prague, region 10'
|
||
custodian_name:
|
||
claim_type: custodian_name
|
||
claim_value: Ústřední archiv zeměměřictví a katastru
|
||
source_type: ch_annotator
|
||
identifiers:
|
||
- identifier_scheme: GHCID
|
||
identifier_value: CZ-10-PRA-A-UAZK
|
||
- identifier_scheme: GHCID_UUID
|
||
identifier_value: 651cc53a-5ead-57c0-b772-2eac68c75974
|
||
- identifier_scheme: GHCID_UUID_SHA256
|
||
identifier_value: 52e8e5e6-422c-86a2-9859-d56ebafa79bb
|
||
- identifier_scheme: GHCID_NUMERIC
|
||
identifier_value: '5974277682822411938'
|
||
- identifier_scheme: RECORD_ID
|
||
identifier_value: 356e9433-489a-42e7-a01c-ce786ae44072
|
||
- *id001
|
||
- *id002
|
||
- *id003
|
||
- *id004
|
||
provenance:
|
||
data_source: API_SCRAPING
|
||
data_tier: TIER_1_AUTHORITATIVE
|
||
extraction_date: '2025-11-19T11:35:45.745597+00:00'
|
||
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
|
||
confidence_score: 0.85
|
||
notes:
|
||
- 'Country resolved 2025-12-06T23:54:40Z: XX→CZ via Wikidata P17'
|
||
- 'YouTube/Google Maps enrichment 2025-12-08T19:48:35Z: Maps: rejected by LLM; YouTube: not found'
|
||
- 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.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: '2025-11-19T11:35:45.745597+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: Ústřední archiv zeměměřictví a katastru
|
||
property_uri: skos:prefLabel
|
||
provenance:
|
||
namespace: glam
|
||
path: /files/czech_unified.yaml
|
||
timestamp: '2025-11-19T11:35:45.745597+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: '2025-11-19T11:35:45.745597+00:00'
|
||
agent: claude-conversation
|
||
context_convention: ch_annotator-v1_7_0
|
||
confidence: 0.95
|
||
- claim_type: wikidata_id
|
||
claim_value: Q61719003
|
||
property_uri: owl:sameAs
|
||
provenance:
|
||
namespace: wikidata
|
||
path: /entity/Q61719003
|
||
timestamp: '2025-11-19T11:35:45.745597+00:00'
|
||
agent: claude-conversation
|
||
context_convention: ch_annotator-v1_7_0
|
||
confidence: 0.98
|
||
integration_note:
|
||
created_from: czech_unified_ch_annotator.yaml
|
||
creation_date: '2025-12-06T23:37:44.868053+00:00'
|
||
creation_method: create_custodian_from_ch_annotator.py
|
||
wikidata_enrichment:
|
||
wikidata_entity_id: Q61719003
|
||
api_metadata:
|
||
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
|
||
fetch_timestamp: '2025-12-08T23:41:29.377000+00:00'
|
||
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
|
||
enrichment_version: 2.0_full
|
||
properties_found:
|
||
- P31
|
||
- P17
|
||
- P18
|
||
- P214
|
||
- P227
|
||
- P856
|
||
- P159
|
||
- P968
|
||
- P361
|
||
- P2671
|
||
wikidata_labels:
|
||
cs: Ústřední archiv zeměměřictví a katastru
|
||
de: Zentralarchiv für Landesvermessung und Kataster
|
||
en: Central Archive of Surveying and Cadastre
|
||
sk: Ústredný archív zememeračstva a katastra
|
||
wikidata_label_en: Central Archive of Surveying and Cadastre
|
||
wikidata_label_de: Zentralarchiv für Landesvermessung und Kataster
|
||
wikidata_descriptions:
|
||
cs: český specializovaný archiv
|
||
sk: český špecializovaný archív
|
||
wikidata_aliases:
|
||
cs:
|
||
- ÚAZK
|
||
- Ústřední archiv zeměměřičství a katastru
|
||
sk:
|
||
- ÚAZK
|
||
wikidata_sitelinks:
|
||
cswiki: Ústřední archiv zeměměřictví a katastru
|
||
wikidata_classification:
|
||
instance_of: &id005
|
||
- id: Q101470010
|
||
label: specialized archives
|
||
description: type of archives in Czechia
|
||
wikidata_instance_of: *id005
|
||
wikidata_location:
|
||
country: &id006
|
||
id: Q213
|
||
label: Czech Republic
|
||
description: country in Central Europe
|
||
headquarters_location:
|
||
id: Q1085
|
||
label: Prague
|
||
description: capital city of the Czech Republic
|
||
wikidata_country: *id006
|
||
wikidata_organization:
|
||
part_of:
|
||
id: Q58490757
|
||
label: Zeměměřický úřad
|
||
description: Czech company
|
||
wikidata_web:
|
||
official_website: https://www.cuzk.cz/Urady/Zememericky-urad/Dalsi-informace/UAZK/Prohlizeni-archivalii,-archivni-mapy.aspx
|
||
wikidata_official_website: https://www.cuzk.cz/Urady/Zememericky-urad/Dalsi-informace/UAZK/Prohlizeni-archivalii,-archivni-mapy.aspx
|
||
wikidata_media:
|
||
image: Křižovatka Střelničná, katastrální úřady.jpg
|
||
wikidata_image: Křižovatka Střelničná, katastrální úřady.jpg
|
||
wikidata_contact:
|
||
email: mailto:miroslav.kronus@cuzk.cz
|
||
google_maps_status: NO_MATCH
|
||
google_maps_rejected:
|
||
candidate_name: Central Military Archives
|
||
rejection_reason: The Google Maps candidate, 'Central Military Archives', does not match the source institution, 'Ústřední
|
||
archiv zeměměřictví a katastru' (Central Archive of Surveying and Cadastre). Although both are archives in Prague, the
|
||
names and institutional focus are different. The Google candidate is military-focused, while the source is focused on
|
||
geodesy and land registry. Therefore, these are two different institutions.
|
||
timestamp: '2025-12-08T19:48:35.122961+00:00'
|
||
youtube_status: NOT_FOUND
|
||
youtube_search_query: Ústřední archiv zeměměřictví a katastru official
|
||
youtube_search_timestamp: '2025-12-08T19:48:35.468025+00:00'
|
||
location:
|
||
region_code: 10
|
||
country: CZ
|
||
normalization_timestamp: '2025-12-09T20:40:58.299005+00:00'
|
||
latitude: 50.08804
|
||
longitude: 14.42076
|
||
city: Prague
|
||
geonames_id: 3067696
|
||
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: '2025-12-09T20:40:58.298985+00:00'
|