dee7a4c7d9
- Improved city name normalization to handle: - St. Gallen / St.Gallen -> Sankt Gallen - Canton suffixes (Buchs SG, Brugg AG) - Hyphenated districts (Bernex - Genève) - Postal codes with slashes (Ecublens/VD) - German prepositions (Hausen b. Brugg) - Created scripts/geocode_from_city_name.py for unified geocoding
151 lines
6 KiB
YAML
151 lines
6 KiB
YAML
original_entry:
|
||
name: 'Lib4Ri: PSI ‒ Library for the Research Institutes within the ETH Domain: Eawag, Empa, PSI & WSL'
|
||
institution_type: LIBRARY
|
||
source: CH-Annotator (switzerland_isil_ch_annotator.yaml)
|
||
identifiers:
|
||
- &id001
|
||
identifier_scheme: ISIL
|
||
identifier_value: CH-000627-4
|
||
identifier_url: https://www.isil.nb.admin.ch/en/?isil=CH-000627-4
|
||
- &id002
|
||
identifier_scheme: Website
|
||
identifier_value: https://www.lib4ri.ch/
|
||
identifier_url: https://www.lib4ri.ch/
|
||
locations:
|
||
- region: AG
|
||
country: CH
|
||
city: Villigen PSI
|
||
postal_code: '5232'
|
||
street_address: Forschungsstrasse 111
|
||
processing_timestamp: '2025-12-06T23:39:11.915881+00:00'
|
||
ghcid:
|
||
ghcid_current: CH-AG-VP-L-LPLRIWEDEE
|
||
ghcid_original: CH-AG-XXX-L-LPLRIWEDEE
|
||
ghcid_uuid: 4efc3ef6-9576-5b0f-8204-caad6131dc84
|
||
ghcid_uuid_sha256: 0d81834f-1df6-8fec-9218-b060b4edc223
|
||
ghcid_numeric: 973203370317107180
|
||
record_id: 73d85df3-c1b1-440f-befc-4a70bb0462b2
|
||
generation_timestamp: '2025-12-06T23:39:11.915881+00:00'
|
||
location_resolution:
|
||
method: SWISS_ISIL_ENRICHMENT
|
||
city_name: Villigen PSI
|
||
city_code: VP
|
||
region_code: AG
|
||
country_code: CH
|
||
enrichment_date: '2025-12-07T00:32:00.136495+00:00'
|
||
source_url: https://www.isil.nb.admin.ch/en/institutions/lib4ri-psi-library-for-the-research-institutes-within-the-eth-domain-eawag-empa-psi-wsl-ch-000627-4/?page=57
|
||
ghcid_history:
|
||
- ghcid: CH-AG-VP-L-LPLRIWEDEE
|
||
ghcid_numeric: 973203370317107180
|
||
valid_from: '2025-12-07T00:32:00.136495+00:00'
|
||
valid_to:
|
||
reason: 'City code updated from Swiss ISIL enrichment: Villigen PSI -> VP'
|
||
- ghcid: CH-AG-XXX-L-LPLRIWEDEE
|
||
ghcid_numeric: 15885979013268324126
|
||
valid_from: '2025-12-06T23:39:11.915881+00:00'
|
||
reason: Initial GHCID from CH-Annotator (switzerland_isil_ch_annotator.yaml)
|
||
valid_to: '2025-12-07T00:32:00.136495+00:00'
|
||
custodian_name:
|
||
claim_type: custodian_name
|
||
claim_value: 'Lib4Ri: PSI ‒ Library for the Research Institutes within the ETH Domain: Eawag, Empa, PSI & WSL'
|
||
source_type: ch_annotator
|
||
identifiers:
|
||
- identifier_scheme: GHCID
|
||
identifier_value: CH-AG-VP-L-LPLRIWEDEE
|
||
- identifier_scheme: GHCID_UUID
|
||
identifier_value: 3a089c70-cfb4-57fe-bbb2-f6dcb3ae4dea
|
||
- identifier_scheme: GHCID_UUID_SHA256
|
||
identifier_value: dc7655be-bb2b-8f1e-d0e5-6607c6bea501
|
||
- identifier_scheme: GHCID_NUMERIC
|
||
identifier_value: '15885979013268324126'
|
||
- identifier_scheme: RECORD_ID
|
||
identifier_value: 73d85df3-c1b1-440f-befc-4a70bb0462b2
|
||
- *id001
|
||
- *id002
|
||
provenance:
|
||
data_source: CSV_REGISTRY
|
||
data_tier: TIER_1_AUTHORITATIVE
|
||
extraction_date: '2025-11-19T09:22:31.452209'
|
||
extraction_method: 'Created from CH-Annotator file: switzerland_isil_ch_annotator.yaml'
|
||
confidence_score: 0.95
|
||
notes:
|
||
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:10:57Z
|
||
- 'YouTube/Google Maps enrichment 2025-12-08T23:19:34Z: Maps: rejected by LLM; YouTube: not found'
|
||
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:47:05Z
|
||
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:48:31Z
|
||
ch_annotator:
|
||
convention_id: ch_annotator-v1_7_0
|
||
convention_version: 1.7.0
|
||
entity_classification:
|
||
hypernym: GRP
|
||
hypernym_label: GROUP
|
||
subtype: GRP.HER.LIB
|
||
subtype_label: LIBRARY
|
||
ontology_class: schema:Library
|
||
alternative_classes:
|
||
- org:FormalOrganization
|
||
- rov:RegisteredOrganization
|
||
- glam:HeritageCustodian
|
||
extraction_provenance:
|
||
namespace: glam
|
||
path: /files/switzerland_isil.yaml
|
||
timestamp: '2025-11-19T09:22:31.452209'
|
||
agent: claude-conversation
|
||
context_convention: ch_annotator-v1_7_0
|
||
annotation_provenance:
|
||
annotation_agent: opencode-claude-sonnet-4
|
||
annotation_date: '2025-12-06T21:13:14.508879+00:00'
|
||
annotation_method: retroactive CH-Annotator application via batch script
|
||
source_file: switzerland_isil.yaml
|
||
annotation_metadata:
|
||
confidence_score: 0.95
|
||
verified: false
|
||
verification_date:
|
||
verified_by:
|
||
entity_claims:
|
||
- claim_type: full_name
|
||
claim_value: 'Lib4Ri: PSI ‒ Library for the Research Institutes within the ETH Domain: Eawag, Empa, PSI & WSL'
|
||
property_uri: skos:prefLabel
|
||
provenance:
|
||
namespace: glam
|
||
path: /files/switzerland_isil.yaml
|
||
timestamp: '2025-11-19T09:22:31.452209'
|
||
agent: claude-conversation
|
||
context_convention: ch_annotator-v1_7_0
|
||
confidence: 0.95
|
||
- claim_type: institution_type
|
||
claim_value: LIBRARY
|
||
property_uri: rdf:type
|
||
provenance:
|
||
namespace: glam
|
||
path: /files/switzerland_isil.yaml
|
||
timestamp: '2025-11-19T09:22:31.452209'
|
||
agent: claude-conversation
|
||
context_convention: ch_annotator-v1_7_0
|
||
confidence: 0.95
|
||
integration_note:
|
||
created_from: switzerland_isil_ch_annotator.yaml
|
||
creation_date: '2025-12-06T23:39:11.915881+00:00'
|
||
creation_method: create_custodian_from_ch_annotator.py
|
||
location:
|
||
city: Villigen PSI
|
||
region: AG
|
||
region_code: AG
|
||
country: CH
|
||
postal_code: '5232'
|
||
street_address: Forschungsstrasse 111
|
||
normalization_timestamp: '2025-12-09T13:21:17.061022+00:00'
|
||
latitude: 47.52682
|
||
longitude: 8.21486
|
||
geonames_id: 2658120
|
||
geocoding_timestamp: '2025-12-09T21:28:09.008782+00:00'
|
||
geocoding_method: CITY_NAME_LOOKUP
|
||
geonames_matched_name: Villigen
|
||
google_maps_status: NO_MATCH
|
||
google_maps_rejected:
|
||
candidate_name: Paul Scherrer Institute
|
||
rejection_reason: 'REJECT. While the location matches perfectly, the names are for different entities. The source institution is ''Lib4Ri: PSI'', a specific library. The Google candidate is ''Paul Scherrer Institute'' (PSI), the larger research institution that *contains* the library. The Google Place type ''point_of_interest, establishment'' also lacks ''library'', failing the type match criterion.'
|
||
timestamp: '2025-12-08T23:19:34.522244+00:00'
|
||
youtube_status: NOT_FOUND
|
||
youtube_search_query: 'Lib4Ri: PSI ‒ Library for the Research Institutes within the ETH Domain: Eawag, Empa, PSI & WSL official'
|
||
youtube_search_timestamp: '2025-12-08T23:19:34.846337+00:00'
|