Triple

T14075017
Position Surface form Disambiguated ID Type / Status
Subject Texas Carnival E338708 entity
Predicate director P255 FINISHED
Object Charles Walters E67570 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: Charles Walters | Statement: [Texas Carnival, director, Charles Walters]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charles Walters
Context triple: [Texas Carnival, director, Charles Walters]
  • A. Charles Walters chosen
    Charles Walters was an American film director and choreographer best known for his work on classic MGM musicals in the mid-20th century.
  • B. Dan Woolsey
    Dan Woolsey is an entrepreneur and media professional best known as a founder of the African American–focused news and entertainment platform TheGrio.
  • C. Walter Sillers
    Walter Sillers was a prominent Mississippi political figure whose influence and legacy in the state led to major public buildings being named in his honor.
  • D. Donald Cargill
    Donald Cargill was a 17th-century Scottish Presbyterian minister and Covenanter leader known for his fierce opposition to royal interference in the church and his eventual execution for treason.
  • E. Hank Corwin
    Hank Corwin is an acclaimed American film editor known for his impressionistic, nonlinear cutting style on films such as The Tree of Life, The Big Short, and Vice.
  • 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_69d81c687b0c819087fd9ed4198403f8 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de5c5bc49881909012b66fa451f495 completed April 14, 2026, 3:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6476c15881909881b9f85697a9b2 completed May 8, 2026, 4:20 a.m.
Created at: April 9, 2026, 10:21 p.m.