Triple

T22307907
Position Surface form Disambiguated ID Type / Status
Subject Karl Childers E551432 entity
Predicate protects P1040 FINISHED
Object Frank Wheatley 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: Frank Wheatley | Statement: [Karl Childers, protects, Frank Wheatley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Wheatley
Context triple: [Karl Childers, protects, Frank Wheatley]
  • A. Frank Wheatley chosen
    Frank Wheatley is a fictional character portrayed by Lucas Black, best known as the young boy who befriends the main character in the film "Sling Blade."
  • B. Loyd Wheaton
    Loyd Wheaton was a U.S. Army general who played a prominent leadership role in the Philippine–American War, particularly during the Luzon campaign.
  • C. Joseph Wightman
    Joseph Wightman was a British Army officer best known for commanding government forces against the Jacobites during the early 18th-century uprisings.
  • D. John Willett
    John Willett is a notable individual distinguished enough to be recognized as a prominent bearer of the surname Willett.
  • E. Walter Graham
    Walter Graham was the husband of American film and television actress Peggie Castle, known for her roles in Westerns and crime dramas of the 1940s–1960s.
  • 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_69e11e46c0188190800181a4233f28fe completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1574bccb08190a6236dd14cf0fc5b completed April 29, 2026, 12:56 a.m.
Created at: April 16, 2026, 8:41 p.m.