Triple

T1518422
Position Surface form Disambiguated ID Type / Status
Subject The Lion King E32171 entity
Predicate voiceCastMember P9616 FINISHED
Object Cheech Marin E68993 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: Cheech Marin | Statement: [The Lion King, voiceCastMember, Cheech Marin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cheech Marin
Context triple: [The Lion King, voiceCastMember, Cheech Marin]
  • A. Cheech Marin chosen
    Cheech Marin is an American comedian and actor best known as half of the stoner comedy duo Cheech & Chong and for his numerous film and television roles.
  • B. Chico Del Vec
    Chico Del Vec is a rapper best known as a member of the Brooklyn hip hop collective Junior M.A.F.I.A.
  • C. Flaco Jiménez
    Flaco Jiménez is a renowned Tex-Mex and conjunto accordionist celebrated for his influential collaborations across country, rock, and Latin music.
  • D. George Lopez
    George Lopez is an American comedian and actor known for his stand-up focusing on Mexican-American culture and for creating and starring in the sitcom "George Lopez."
  • E. John Leguizamo
    John Leguizamo is a Colombian-American actor, comedian, and producer known for his energetic character roles in film, television, and theater, as well as his acclaimed one-man shows.
  • 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_69a885e8caf88190a5fbb6159ce87786 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a907ed44ac8190953e428c831e24df completed March 5, 2026, 4:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad2346e7b481909c105a969724591d completed March 8, 2026, 7:20 a.m.
Created at: March 4, 2026, 7:26 p.m.