Triple

T22402362
Position Surface form Disambiguated ID Type / Status
Subject Order of Calatrava E553790 entity
Predicate notableStronghold P26618 FINISHED
Object Calatrava la Vieja NE NERFINISHED

How this triple was built (2 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: Calatrava la Vieja | Statement: [Order of Calatrava, notableStronghold, Calatrava la Vieja]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Calatrava la Vieja
Context triple: [Order of Calatrava, notableStronghold, Calatrava la Vieja]
  • A. Calatrava la Vieja chosen
    Calatrava la Vieja is a historic medieval fortress and former town in central Spain that served as the original stronghold and namesake of the military Order of Calatrava.
  • B. Spanish Tower
    Spanish Tower is a historic defensive tower that forms part of the medieval Bodrum Castle complex in Bodrum, Turkey.
  • C. Torre de Bujaco
    Torre de Bujaco is a prominent medieval defensive tower in Cáceres, Spain, notable for its well-preserved architecture and role as an emblem of the city’s historic skyline.
  • D. Torre de Don Miguel
    Torre de Don Miguel is a historic rural village in the Sierra de Gata region of Extremadura, Spain, known for its traditional stone architecture and scenic mountain surroundings.
  • E. La Almudena
    La Almudena is a Madrid Metro station on the city’s Line 2 serving the eastern part of the Spanish capital.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e4da7048190b4387d422a9a0de5 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f158b565c48190b0f6c19f17995b40 completed April 29, 2026, 1:02 a.m.
Created at: April 16, 2026, 8:46 p.m.