Triple

T20287007
Position Surface form Disambiguated ID Type / Status
Subject Mad Cows E509907 entity
Predicate cinematographyBy P1953 FINISHED
Object David Odd 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: David Odd | Statement: [Mad Cows, cinematographyBy, David Odd]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Odd
Context triple: [Mad Cows, cinematographyBy, David Odd]
  • A. David Odd chosen
    David Odd is a cinematographer known for his work on the film "Mad Cows."
  • B. David Hodo
    David Hodo is an American singer and performer best known as the construction worker character in the disco group Village People.
  • C. David Hankins
    David Hankins is a film editor best known for his work on the 1986 animated feature "Transformers: The Movie."
  • D. Steven Stroud
    Steven Stroud is an American illustrator and cover artist known for his work on numerous science fiction and fantasy book covers.
  • E. David Schearl
    David Schearl is the introspective, anxiety-ridden Jewish immigrant boy whose experiences in early 20th-century New York City form the emotional core of Henry Roth’s novel "Call It Sleep."
  • 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_69e0b4c652388190b782cad965e5a098 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e676931fe08190b278d829a745701f completed April 20, 2026, 6:55 p.m.
Created at: April 16, 2026, 11:07 a.m.