Triple

T17806266
Position Surface form Disambiguated ID Type / Status
Subject George Butler E444567 entity
Predicate coWorkedWith P26607 FINISHED
Object Charles Gaines 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: Charles Gaines | Statement: [George Butler, coWorkedWith, Charles Gaines]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charles Gaines
Context triple: [George Butler, coWorkedWith, Charles Gaines]
  • A. Charles Gaines chosen
    Charles Gaines is an American author and screenwriter best known for co-writing the influential bodybuilding book and film "Pumping Iron."
  • B. Glenn Ligon
    Glenn Ligon is an American conceptual artist known for his text-based paintings and installations that explore race, language, identity, and the politics of representation.
  • C. Titus Kaphar
    Titus Kaphar is a contemporary American artist known for reimagining and altering historical paintings to highlight overlooked Black figures and critique the narratives of Western art history.
  • D. Mark Bradford
    Mark Bradford is an American contemporary artist renowned for his large-scale abstract mixed-media collages and installations that explore race, class, and urban experience.
  • E. Ed Moses
    Ed Moses was an influential American abstract painter associated with the Los Angeles art scene and the West Coast’s postwar avant-garde.
  • 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_69d8b9efe370819095cd219b143ae727 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e488044cdc8190a09a2265c8a86475 completed April 19, 2026, 7:45 a.m.
Created at: April 10, 2026, 10:14 a.m.