Triple

T18929047
Position Surface form Disambiguated ID Type / Status
Subject Francisco de Asís Martínez-Bordiú y Franco E463049 entity
Predicate familyName P18 FINISHED
Object Franco 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: Franco | Statement: [Francisco de Asís Martínez-Bordiú y Franco, familyName, Franco]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Franco
Context triple: [Francisco de Asís Martínez-Bordiú y Franco, familyName, Franco]
  • A. Franco chosen
    Franco is a common Spanish surname borne by numerous notable figures across politics, arts, and sports.
  • B. Franco
    Franco is the given name of Franco Harris, the Hall of Fame NFL running back best known for the “Immaculate Reception” with the Pittsburgh Steelers.
  • C. Benito
    Benito is the given name of Benito Mussolini, the Italian dictator who founded and led the National Fascist Party and ruled Italy from the 1920s until 1943.
  • D. Ferdinande
    Ferdinande is the given name of Archduchess Auguste Ferdinande of Austria, a 19th-century member of the Habsburg-Lorraine dynasty.
  • E. Francesco Francia
    Francesco Francia was an Italian Renaissance painter and goldsmith from Bologna, known for his refined religious altarpieces and influential role in the Bolognese school of painting.
  • 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_69d8dcfdbbb881909964fa5a75bd0b48 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c9bea84081908fbe657fb4657c0b completed April 20, 2026, 6:37 a.m.
Created at: April 10, 2026, 11:59 a.m.