Triple

T23499632
Position Surface form Disambiguated ID Type / Status
Subject John of Capistrano E571803 entity
Predicate birthPlace P1 FINISHED
Object Capestrano 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: Capestrano | Statement: [John of Capistrano, birthPlace, Capestrano]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Capestrano
Context triple: [John of Capistrano, birthPlace, Capestrano]
  • A. Capestrano chosen
    Capestrano is a small historic town in Italy’s Abruzzo region, known for its medieval architecture and religious heritage.
  • B. Molinara
    Molinara is a light-colored Italian red wine grape variety traditionally used in blends from the Veneto region, particularly in wines like Bardolino and Valpolicella.
  • C. Landino
    Landino is an Italian surname most notably associated with the Renaissance humanist and scholar Cristoforo Landino.
  • D. Cappadora
    Cappadora is an Italian-origin surname most notably associated with the fictional family in Jacquelyn Mitchard’s novel "The Deep End of the Ocean."
  • E. Nocciano
    Nocciano is a small Italian town and comune in the Abruzzo region, known for its historic hilltop setting and traditional rural character.
  • 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_69e245b4829881909b77a70e942bbd54 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a8fb71c08190a30500b3f63a9ce6 completed April 29, 2026, 6:45 a.m.
Created at: April 17, 2026, 6:06 p.m.