Triple

T21563617
Position Surface form Disambiguated ID Type / Status
Subject Perlak E532103 entity
Predicate locatedIn P40 FINISHED
Object San Sebastián
San Sebastián is a coastal city in northern Spain’s Basque Country, renowned for its picturesque bay, vibrant cultural scene, and world-class cuisine.
 E138087 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: San Sebastián | Statement: [Perlak, locatedIn, San Sebastián]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: San Sebastián
Context triple: [Perlak, locatedIn, San Sebastián]
  • A. San Sebastián
    San Sebastián is a small town located within the Comayagua Department of central Honduras.
  • B. San Sebastián
    San Sebastián is a Guatemalan town located in the highlands of the San Marcos department, known for its proximity to Central America’s highest peak, Volcán Tajumulco.
  • C. San Sebastián
    San Sebastián is a district and urban area within the San José metropolitan region of Costa Rica, known for its residential neighborhoods and proximity to the country’s capital.
  • D. Donostia-San Sebastián
    Donostia-San Sebastián is a coastal city in Spain’s Basque Country renowned for its picturesque bay, beaches, and world-class gastronomy.
  • E. Bilbao
    Bilbao is a station on Madrid's Metro network, serving Line 1 and located in the central Chamberí district.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: San Sebastián
Triple: [Perlak, locatedIn, San Sebastián]
Generated description
San Sebastián is a coastal city in northern Spain’s Basque Country, renowned for its picturesque bay, vibrant cultural scene, and world-class cuisine.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: San Sebastián
Target entity description: San Sebastián is a coastal city in northern Spain’s Basque Country, renowned for its picturesque bay, vibrant cultural scene, and world-class cuisine.
  • A. San Sebastián
    San Sebastián is a Guatemalan town located in the highlands of the San Marcos department, known for its proximity to Central America’s highest peak, Volcán Tajumulco.
  • B. San Sebastián
    San Sebastián is a small town located within the Comayagua Department of central Honduras.
  • C. San Sebastián
    San Sebastián is a district and urban area within the San José metropolitan region of Costa Rica, known for its residential neighborhoods and proximity to the country’s capital.
  • D. Donostia-San Sebastián chosen
    Donostia-San Sebastián is a coastal city in Spain’s Basque Country renowned for its picturesque bay, beaches, and world-class gastronomy.
  • E. Bilbao
    Bilbao is a station on Madrid's Metro network, serving Line 1 and located in the central Chamberí district.
  • F. None of above.

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e0c460db088190828c64206a450273 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eed2e6c19c81909eaae408d94f0625 completed April 27, 2026, 3:07 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09eeed4f908190b31dfbdfd5c6221b completed May 17, 2026, 4:38 p.m.
NEDg Description generation batch_6a09f004a6d081909f78953ca8daea39 completed May 17, 2026, 4:42 p.m.
NED2 Entity disambiguation (via description) batch_6a09f07a090c8190aead09c3b06e0e34 completed May 17, 2026, 4:44 p.m.
Created at: April 16, 2026, 6:29 p.m.