Triple

T14235198
Position Surface form Disambiguated ID Type / Status
Subject Race to Witch Mountain E352858 entity
Predicate starring P1507 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: [Race to Witch Mountain, starring, Cheech Marin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cheech Marin
Context triple: [Race to Witch Mountain, starring, 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. Tommy Chong
    Tommy Chong is a Canadian-American comedian, actor, and musician best known as half of the stoner comedy duo Cheech & Chong.
  • C. Don Goyo
    Don Goyo is the affectionate local nickname for Popocatépetl, the active volcano near Mexico City that holds great cultural and spiritual significance in Mexican tradition.
  • D. Terry Cheek
    Terry Cheek is a film editor known for his work on the sequel comedy-drama "More American Graffiti."
  • E. Corky Gonzales
    Corky Gonzales was a prominent Chicano activist, poet, and political organizer whose work and writings helped shape the ideology and momentum of the Chicano movement in the United States.
  • 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_69d8278adc7c8190a9218d69bce3c4e6 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de62411c888190a154acd56fe3fcaf completed April 14, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd281da708819082f5aefb7ad7b30b completed May 8, 2026, 12:02 a.m.
Created at: April 10, 2026, 1:07 a.m.