d9325c0bb5
Backend: - Attach web_archives.duckdb as read-only database in DuckLake - Create views for web_archives, web_pages, web_claims in heritage schema Scripts: - enrich_cities_google.py: Add batch processing and retry logic - migrate_web_archives.py: Improve schema handling and error recovery Frontend: - DuckLakePanel: Add web archives query support - Database.css: Improve layout for query results display
145 lines
5.3 KiB
YAML
145 lines
5.3 KiB
YAML
ch_annotator:
|
|
annotation_metadata:
|
|
confidence_score: 0.7
|
|
verification_date: null
|
|
verified: false
|
|
verified_by: null
|
|
annotation_provenance:
|
|
annotation_agent: opencode-claude-sonnet-4
|
|
annotation_date: '2025-12-06T21:13:56.173868+00:00'
|
|
annotation_method: retroactive CH-Annotator application via batch script
|
|
source_file: latin_american_institutions_AUTHORITATIVE.yaml
|
|
convention_id: ch_annotator-v1_7_0
|
|
convention_version: 1.7.0
|
|
entity_claims:
|
|
- claim_type: full_name
|
|
claim_value: UFMG Tainacan Lab
|
|
confidence: 0.7
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555330+00:00'
|
|
- claim_type: institution_type
|
|
claim_value: EDUCATION_PROVIDER
|
|
confidence: 0.95
|
|
property_uri: rdf:type
|
|
provenance:
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555330+00:00'
|
|
- claim_type: ghcid
|
|
claim_value: BR-MG-XXX-E-UTL
|
|
confidence: 1.0
|
|
property_uri: glam:ghcid
|
|
provenance:
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555330+00:00'
|
|
entity_classification:
|
|
alternative_classes:
|
|
- org:FormalOrganization
|
|
- rov:RegisteredOrganization
|
|
- glam:HeritageCustodian
|
|
hypernym: GRP
|
|
hypernym_label: GROUP
|
|
ontology_class: schema:EducationalOrganization
|
|
subtype: GRP.EDU
|
|
subtype_label: EDUCATION_PROVIDER
|
|
extraction_provenance:
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555330+00:00'
|
|
integration_note:
|
|
created_from: latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:35:51.880783+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: UFMG Tainacan Lab
|
|
source_type: ch_annotator
|
|
ghcid:
|
|
generation_timestamp: '2025-12-06T23:35:51.880783+00:00'
|
|
ghcid_current: BR-MG-BHO-E-UTL
|
|
ghcid_history:
|
|
- ghcid: BR-MI-XXX-E-UTL
|
|
ghcid_numeric: 5713454927958947773
|
|
reason: Initial GHCID from CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
|
|
valid_from: '2025-12-06T23:35:51.880783+00:00'
|
|
ghcid_numeric: 5713454927958947773
|
|
ghcid_original: BR-MI-XXX-E-UTL
|
|
ghcid_uuid: 562718ae-1d5c-57d7-9829-db40b4242ad1
|
|
ghcid_uuid_sha256: 4f4a44fc-5d32-87bd-c800-efcba8b8407d
|
|
location_resolution:
|
|
city_code: BHO
|
|
city_name: Belo Horizonte
|
|
country_code: BR
|
|
geonames_id: 3470127
|
|
google_maps_url: https://maps.app.goo.gl/LqXWAtMukbvr4e5AA
|
|
latitude: -19.8697
|
|
longitude: -43.9637
|
|
method: MANUAL_RESEARCH
|
|
notes: Tainacan Lab at UFMG School of Information Science (Escola de Ciência da
|
|
Informação)
|
|
region_code: MG
|
|
region_name: Minas Gerais
|
|
resolution_date: '2025-12-07T16:44:07.052938+00:00'
|
|
record_id: 3c8e1c49-716c-40ea-a283-a208686138b7
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: BR-MG-BHO-E-UTL
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 562718ae-1d5c-57d7-9829-db40b4242ad1
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 4f4a44fc-5d32-87bd-c800-efcba8b8407d
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '5713454927958947773'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 3c8e1c49-716c-40ea-a283-a208686138b7
|
|
- &id001
|
|
identifier_scheme: OLD_ID
|
|
identifier_value: https://w3id.org/heritage/custodian/br/ufmg-tainacan-lab
|
|
- &id002
|
|
identifier_scheme: OLD_ID
|
|
identifier_value: 12840343882751256357
|
|
- identifier_scheme: Website
|
|
identifier_url: https://tainacan.eci.ufmg.br/
|
|
identifier_value: https://tainacan.eci.ufmg.br/
|
|
original_entry:
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: BR-MG-XXX-E-UTL
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '12840343882751256357'
|
|
- *id001
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_url: urn:uuid:5ce7af22-178b-513d-8ec6-0d84cd016a81
|
|
identifier_value: 5ce7af22-178b-513d-8ec6-0d84cd016a81
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_url: urn:uuid:b23210ba-f53f-8725-b6b1-8967118aaa2b
|
|
identifier_value: b23210ba-f53f-8725-b6b1-8967118aaa2b
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_url: urn:uuid:019a58fd-3226-75d2-a0d2-900b91512f20
|
|
identifier_value: 019a58fd-3226-75d2-a0d2-900b91512f20
|
|
- *id002
|
|
institution_type: EDUCATION_PROVIDER
|
|
locations:
|
|
- country: BR
|
|
region: MINAS GERAIS
|
|
name: UFMG Tainacan Lab
|
|
source: CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
|
|
processing_timestamp: '2025-12-06T23:35:51.880783+00:00'
|
|
provenance:
|
|
confidence_score: 0.7
|
|
data_source: CONVERSATION_NLP
|
|
data_tier: TIER_4_INFERRED
|
|
extraction_date: '2025-11-06T08:25:13.555330+00:00'
|
|
extraction_method: 'Created from CH-Annotator file: latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml'
|