glam/data/custodian.backup.20251230/CZ-10-PRA-A-NULK.yaml
2025-12-30 23:07:03 +01:00

288 lines
13 KiB
YAML
Raw Permalink Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

custodian_name:
claim_type: custodian_name
claim_value: Národní ústav lidové kultury
source_type: ch_annotator
original_entry:
name: Národní ústav lidové kultury
institution_type: ARCHIVE
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: ARON_UUID
identifier_value: 46dbcaf2-b1c8-4004-b2da-b4e2adf337d8
identifier_url: https://portal.nacr.cz/aron/apu/46dbcaf2-b1c8-4004-b2da-b4e2adf337d8
- &id002
identifier_scheme: INSTITUTION_CODE
identifier_value: '906205030'
locations: []
processing_timestamp: '2025-12-06T23:37:44.090204+00:00'
ghcid:
ghcid_current: CZ-10-PRA-A-NULK
ghcid_original: XX-XX-XXX-A-NÚLK
ghcid_uuid: d8f0c73c-4055-5208-93d2-fdbbb9e445df
ghcid_uuid_sha256: 654bc5bd-b223-886e-a42e-27b364bd0fca
ghcid_numeric: 7299145039612164206
record_id: ccfc80b1-43cd-4c0d-b45b-03ec7881a943
generation_timestamp: '2025-12-06T23:37:44.090204+00:00'
location_resolution:
country_code: CZ
region_code: 10
city_code: PRA
method: NAME_PATTERN_EXTRACTION
resolution_timestamp: '2025-12-06T23:56:12.055303+00:00'
ghcid_history:
- ghcid: CZ-10-PRA-A-NULK
ghcid_numeric: 7299145039612164206
valid_from: '2025-12-08T11:21:32.697656+00:00'
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-10-PRA-A-NÚLK)'
- ghcid: XX-XX-XXX-A-NÚLK
ghcid_numeric: 12372125188683264797
valid_from: '2025-12-06T23:37:44.090204+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
valid_to: '2025-12-08T11:21:32.697656+00:00'
- ghcid: CZ-XX-XXX-A-NÚLK
valid_from: '2025-12-06T23:56:12.055307+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-10-PRA-A-NÚLK
valid_from: '2025-12-07T12:39:42.487076+00:00'
reason: 'Location resolved from institution name pattern: ''Prague'' → region 10, city PRA'
identifiers:
- identifier_scheme: GHCID
identifier_value: CZ-10-PRA-A-NULK
- identifier_scheme: GHCID_UUID
identifier_value: d8f0c73c-4055-5208-93d2-fdbbb9e445df
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 654bc5bd-b223-886e-a42e-27b364bd0fca
- identifier_scheme: GHCID_NUMERIC
identifier_value: '7299145039612164206'
- identifier_scheme: RECORD_ID
identifier_value: ccfc80b1-43cd-4c0d-b45b-03ec7881a943
- *id001
- *id002
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T11:35:45.744017+00:00'
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
confidence_score: 0.85
notes:
- 'Country resolved 2025-12-06T23:56:12Z: XX→CZ via Wikidata P17'
- 'YouTube/Google Maps enrichment 2025-12-08T19:47:52Z: Maps: The National Institute of Folk Culture (conf: 0.95); YouTube:
not found'
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:11:19Z
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:04Z
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:28Z
schema_version: 2.0.0
enrichment_provenance:
google_maps_enrichment:
content_hash: sha256-IUZv9iXjUJTvOYU6FYpaN4H5QiOyJ0pzVw2f2cnIieI=
verified_at: '2025-12-28T19:58:21.616546+00:00'
provenance_schema_version: '2.0'
standards_compliance:
- W3C PROV-O
- W3C SRI (content hashes)
generated_at: '2025-12-28T19:58:21.616568+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: '2025-11-19T11:35:45.744017+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: Národní ústav lidové kultury
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.744017+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: '2025-11-19T11:35:45.744017+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:44.090204+00:00'
creation_method: create_custodian_from_ch_annotator.py
google_maps_enrichment:
place_id: ChIJoSMNXzE6E0cRPhyYLvDYA78
name: The National Institute of Folk Culture
fetch_timestamp: '2025-12-08T19:47:49.560816+00:00'
api_status: OK
coordinates:
latitude: 48.907858499999996
longitude: 17.3131225
formatted_address: Zámek 672, 696 62 Strážnice, Czechia
short_address: Zámek 672, Strážnice
phone_local: 518 306 611
phone_international: +420 518 306 611
website: http://www.nulk.cz/
google_place_types:
- cultural_center
- historical_landmark
- tourist_attraction
- historical_place
- museum
- point_of_interest
- establishment
primary_type: cultural_center
business_status: OPERATIONAL
rating: 4.7
total_ratings: 37
reviews:
- author_name: Sona Stoiljkovic
author_uri: https://www.google.com/maps/contrib/117683512593957299614/reviews
rating: 5
relative_time_description: 7 years ago
text: Every year, on the last weekend of June, the castle park in Strážnice comes alive with folk music, dance and numerous
programs reminiscent of ancient traditions and customs. Leading folklore groups from Bohemia, Moravia and Silesia
take turns performing in front of the audience on the open-air stage in the amphitheatres, open-air museum and castle.
The weekend program regularly includes performances by a number of foreign folklore groups, which has made the Strážnice
festival one of the most important international festivals for six decades.
publish_time: '2018-09-26T09:18:08.716104Z'
- author_name: Petr Slezáček
author_uri: https://www.google.com/maps/contrib/105891687475984511026/reviews
rating: 5
relative_time_description: 4 years ago
text: Nice place
publish_time: '2021-06-28T20:31:43.735735Z'
- author_name: Václav Krchňáček
author_uri: https://www.google.com/maps/contrib/105456049917812849761/reviews
rating: 5
relative_time_description: 7 years ago
text: Beautiful castle with an adjacent park, ideal for relaxation.
publish_time: '2018-07-13T08:53:57.060Z'
- author_name: Ondřej Kaňa
author_uri: https://www.google.com/maps/contrib/118195677499871115757/reviews
rating: 5
relative_time_description: 6 years ago
text: I only know about the festivities there and only outside under the Šances. So pretty good
publish_time: '2019-09-04T19:09:11.725557Z'
- author_name: františek Ondra
author_uri: https://www.google.com/maps/contrib/112735498518459734845/reviews
rating: 5
relative_time_description: 3 years ago
text: Interesting place, excellent guided tours
publish_time: '2022-05-02T04:45:30.036312Z'
opening_hours:
open_now: false
weekday_text:
- 'Monday: 7:00AM3:30PM'
- 'Tuesday: 7:00AM3:30PM'
- 'Wednesday: 7:00AM3:30PM'
- 'Thursday: 7:00AM3:30PM'
- 'Friday: 7:00AM3:30PM'
- 'Saturday: Closed'
- 'Sunday: Closed'
photo_count: 10
photos_metadata:
- name: places/ChIJoSMNXzE6E0cRPhyYLvDYA78/photos/AZLasHo8Nk_kOQ7lRT7lpQuUlQ9Zi90O1edDAZtcu9TW9yWk-S0z5A03j0UAIhahyeTF3ErZasM7J-df--E21EsmybUKYtQy6Ybrik47O2J5SbjGC-DTBvblJByywIr15A2BF8-KOD3QtTW6xz3_oIqTG6yBcTh3omqLGh7VjDwbl9RYpoR7JhvrLDj7KAxrnOE9yel1QyIN_nnc1G29gL75kQi7ZfWnUkeaaCVYM9nKLPM5eXHH3Pve5JvUPo_fefi86lzF9JRjCsD8oaZpglrfWfBPv-iWHe-w_cfK2EtKdyVfTw
height: 1536
width: 2048
- name: places/ChIJoSMNXzE6E0cRPhyYLvDYA78/photos/AZLasHq-I2BqUu3zCEzBPkQ69sXkLJyQnxp-uHKUEES5aUgk3NG3GXgNWcMjZBhW-N4PbAMi9N9uJPOL--4qvSEVu8FgyZ349k2c6YAyjw52B9tYFBSXQUfWmhtDY2Jfxtz-IZOeHRe0ZhkNCk58kXVr5Fy3hdKr06Lc2smgLVKvInuVfo1flo8zc1DvDrcOcSkHHfQdtGpmSus7Q9dlxpDVFb9PH6V_MA6jqP_J3XKRdzC9FsTnHd4UgTTQNHV7yeusCP5P3Bu7q5fLpHbIseouutxbdYNYO2Plzq_1CFAfqnZp_-q6X9Qw77_gmthIQBU5783P-OtwpG1VSFPRQFa6BNq5X_tSFRgDK2C6TuRDtVr0K5ZnSzGkPYU-OGIwm1zhR4Z9Ov1n_vnOZghgb4rafeG9QuVKZIZ8Jp8Aeix6ztbMUw
height: 2340
width: 4160
- name: places/ChIJoSMNXzE6E0cRPhyYLvDYA78/photos/AZLasHoqskeMVDYqKNvBf_RW7qst-Vjbo2q7HFEuC-JkcXYacadR_e9EkKRx8bDMeb5bZBlW5Zh0-opH4DFeVdHG0FrXV8AwnE88Xc6iuhrv6q2Gzu7h_iodhEGODlBfJm2d89jOUBASt-nne_YrNK0KfJ1ZTyt0kmhykzKaDh4diBIzlhWwFH-Tl7LfKLeeKRKBBsgvf6LGQiHyHEpm-3qDtjgPBQMojCkShUWYjlPbhcaSmJy5Ob71InlCA56KoX186JjgR7j2gBpu-a82cCU5W4yAdlTmBkULXIJbJapp9mBMIwgECXgAMHMkqvvnf-2dI5T8MbHoOYZQxa7GoaSGVUtQ-e0iQYPVS6TaPWHduDxZHboHY_JjUCcozG8kopINCKmUKEzLOKjVVLij8eN6YRU8UKzHz_jZCb8x1acuRhZ5hRQc
height: 2184
width: 4608
- name: places/ChIJoSMNXzE6E0cRPhyYLvDYA78/photos/AZLasHqCFaxwIsvdZykwh7A_th1CS2AxE-fxOu6y82oSg82xEetDKo_Za-IB1qFnFzzbwXEtK5z-lgBuTFY-17EYngP2L87zON2LE3injx8fwmmasHHevXRfAG5Dw21su3oUsDL7kGsGzidIXVXL0-1R6pGnvhvIYW7W8kKyDqWScl4CAnKm6hAJA7qFtj2sCeFihaBUdpFPdEWFbkCD4bYgNbwXYovoqg50r4HRbut54RD3gPweOu8mM8a9hUUwsmf-j1IAMdFzoeEOYc0GZ1CZHAZLwGjROoW10S8XATokimWhjgfhISput8ZS9A8_rkJjmmxMAOYjZViZqr-LkkEHNLRM7jQOZqqc6t2tYpBwPs-GEp4faj4nhQUSuuQoB_Xq13LtHsOp6XHrpzGMUI0IvGnLz9mgfhq4adu61h7daQU
height: 2184
width: 4608
- name: places/ChIJoSMNXzE6E0cRPhyYLvDYA78/photos/AZLasHr57k4iuthpmFev3dsuJhHShK5GZ6dHd8gGIoCsX7R4BUuq627bfFmAFE53Een_7OuIjAX-xHJvcGc7FZz9e31vF-ZKBtsqqjBhkBzCRHewzpaPvNS6RxbounXIJOdlgYsIOr7fzkOp59aLoXYklcGUHwewfCdCz_VoEuj6zeHIvJowaGdEo9nP0RZndmwhgeRq8ZXO1jjImL9pMRKZ5pcpBzj7qjrSGqveeIXvXk7dkNU-kKrS-xoudu3Rne8EuiDsKm3MecsbFNqDA_SYKJ6l95zxqGbSS7AlYJcL85zmhl1gtjJXG-f1wZoVKoEDSZxr2-3u6FtFlTKjynjIry-7U5LpB3YtSysiXfnZmvtN1EgH0h18WSW4ssMaAPYjGulEsZgMrEx6TeTI65uCf08-YWHA97cZdP8HKMGZx1jnLg
height: 768
width: 1024
google_maps_url: https://maps.google.com/?cid=13764083412259839038&g_mp=Cidnb29nbGUubWFwcy5wbGFjZXMudjEuUGxhY2VzLlNlYXJjaFRleHQQAhgEIAA
llm_verification:
is_match: true
confidence: 0.95
entity_type: GRP.HER
reasoning: The Google candidate is a direct translation of the source institution's name. The website (www.nulk.cz) is
a strong confirmation of the match. The location in Czechia is correct. The 'museum' Google Place type matches the expected
GRP.HER type.
agent: glm-4.6
verified: true
ch_annotator_version: ch_annotator-v1_7_0
_provenance:
content_hash:
algorithm: sha256
value: sha256-IUZv9iXjUJTvOYU6FYpaN4H5QiOyJ0pzVw2f2cnIieI=
scope: enrichment_section
computed_at: '2025-12-28T19:58:21.616546+00:00'
prov:
wasDerivedFrom: https://maps.googleapis.com/maps/api/place/details/json?place_id=ChIJoSMNXzE6E0cRPhyYLvDYA78
generatedAtTime: '2025-12-08T19:47:49.560816+00:00'
wasGeneratedBy:
'@type': prov:Activity
name: google_maps_api_fetch
used: https://maps.googleapis.com/maps/api/place
verification:
status: verified
last_verified: '2025-12-28T19:58:21.616557+00:00'
google_maps_status: SUCCESS
youtube_status: NOT_FOUND
youtube_search_query: Národní ústav lidové kultury official
youtube_search_timestamp: '2025-12-08T19:47:52.050794+00:00'
location:
latitude: 48.907858499999996
longitude: 17.3131225
coordinate_provenance:
source_type: GOOGLE_MAPS
source_path: google_maps_enrichment.coordinates
original_timestamp: '2025-12-08T19:47:49.560816+00:00'
entity_id: ChIJoSMNXzE6E0cRPhyYLvDYA78
region_code: 10
country: CZ
street_address: Zámek 672, Strážnice
formatted_address: Zámek 672, 696 62 Strážnice, Czechia
normalization_timestamp: '2025-12-09T06:49:28.743251+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T20:58:08.250911+00:00'
source_url: http://www.nulk.cz
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.nulk.cz/wp-content/uploads/2016/11/cropped-favicon-180x180.png
source_url: http://www.nulk.cz
css_selector: '[document] > html > head > link:nth-of-type(26)'
retrieved_on: '2025-12-23T20:58:08.250911+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: 3