Triple

T10280646
Position Surface form Disambiguated ID Type / Status
Subject William Holden E241089 entity
Predicate partner P1136 FINISHED
Object Capucine E621817 NE FINISHED

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: Capucine | Statement: [William Holden, partner, Capucine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Capucine
Context triple: [William Holden, partner, Capucine]
  • A. Capucine chosen
    Capucine was a French fashion model and film actress best known for her elegant screen presence in 1960s comedies and dramas, including roles in films like The Pink Panther.
  • B. Zibelle
    Zibelle is a village in eastern Germany, historically part of Lusatia, known in this context as the place where physicist Walther Nernst died.
  • C. Margeride
    Margeride is a mountainous and sparsely populated region in south-central France known for its granite plateaus, forests, and traditional rural landscapes.
  • D. La Belle
    La Belle was a 17th-century French barque used by explorer René-Robert Cavelier, Sieur de La Salle during his ill-fated expedition to establish a colony near the mouth of the Mississippi River.
  • E. Béline
    Béline is the hypocritical and scheming second wife of Argan in Molière’s comedy "Le Malade imaginaire."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d381a94c1881908fc38fc263d9b9c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d2a0c90c8190ad6ee479a32e5a95 completed April 7, 2026, 9:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f82f16688190b1c6b80e424bd552 completed April 9, 2026, 12:51 a.m.
Created at: April 6, 2026, 11:38 a.m.