Triple

T17883180
Position Surface form Disambiguated ID Type / Status
Subject John Guillermin E447140 entity
Predicate familyName P18 FINISHED
Object Guillermin 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: Guillermin | Statement: [John Guillermin, familyName, Guillermin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Guillermin
Context triple: [John Guillermin, familyName, Guillermin]
  • A. Guillermin chosen
    Guillermin is a French-origin surname most notably associated with British film director John Guillermin, known for works such as "The Towering Inferno" and the 1976 remake of "King Kong."
  • B. Dreyen
    Dreyen is a locality or district that forms part of the town of Enger in North Rhine-Westphalia, Germany.
  • C. Saldaña
    Saldaña is a Spanish-language surname most prominently associated with American actress Zoe Saldana.
  • D. Rosson
    Rosson is a surname most notably associated with American cinematographer Harold Rosson, known for his work on classic Hollywood films.
  • E. Cormon
    Cormon is the surname of Fernand Cormon, a notable 19th-century French academic painter known for his historical and biblical scenes and for teaching many influential artists.
  • 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49c1016508190857adce1a0fbb355 completed April 19, 2026, 9:10 a.m.
Created at: April 10, 2026, 10:18 a.m.