Triple

T15964600
Position Surface form Disambiguated ID Type / Status
Subject Anthony Powell E387151 entity
Predicate notableWork P4 FINISHED
Object Papillon E1171400 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: Papillon | Statement: [Anthony Powell, notableWork, Papillon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Papillon
Context triple: [Anthony Powell, notableWork, Papillon]
  • A. Papillon
    Papillon is a 1973 prison escape drama film, starring Steve McQueen and Dustin Hoffman, based on the memoirs of French convict Henri Charrière.
  • B. Papillon chosen
    Papillon is a studio album by Belgian-Canadian singer Lara Fabian that showcases her emotive pop style and powerful vocal performances.
  • C. Le Papillon
    Le Papillon is a 19th-century ballet, best known for its light, fairy-tale atmosphere and melodic score by composer Ludwig Minkus.
  • D. Papillon (aka Hot Butterfly)
    "Papillon (aka Hot Butterfly)" is a soulful disco-influenced track popularized by Chaka Khan, known for its lush production and powerful vocal performance.
  • E. Le Doulos
    Le Doulos is a 1962 French film noir crime thriller by Jean-Pierre Melville, renowned for its moody atmosphere, intricate plot, and exploration of loyalty and betrayal in the Parisian underworld.
  • 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_69d86da94ccc819083d187f5dc6a123e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1572475948190af0e3b12de0f6cea completed April 16, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffbe84f4888190b3fdb5f32763f78d completed May 9, 2026, 11:08 p.m.
Created at: April 10, 2026, 4:54 a.m.