Triple

T8335383
Position Surface form Disambiguated ID Type / Status
Subject Annabelle E195774 entity
Predicate editedBy P1954 FINISHED
Object Tom Elkins E442745 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: Tom Elkins | Statement: [Annabelle, editedBy, Tom Elkins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Elkins
Context triple: [Annabelle, editedBy, Tom Elkins]
  • A. Tom Elkins chosen
    Tom Elkins is a film editor best known for his work in the horror and thriller genres, including editing movies like "Inferno."
  • B. Jim Barnhill
    Jim Barnhill was an American football official best known for serving as a referee in the American Football League during the 1960s.
  • C. Bill Wittliff
    Bill Wittliff was an American screenwriter, author, and photographer best known for adapting and writing acclaimed Western-themed films and television miniseries.
  • D. Ted Daughety
    Ted Daughety is an American physician and pulmonologist best known as the husband of Kansas Governor Laura Kelly.
  • E. Bob Hines
    Bob Hines was an American wildlife artist and illustrator renowned for his detailed depictions of nature in scientific and environmental publications.
  • 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_69ca82ecbdc481908a55cad8ca062d88 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7fd2ca648190991e398ba70caf8d completed March 31, 2026, 8:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69cf5127db38819087d5ba71b6064998 completed April 3, 2026, 5:33 a.m.
Created at: March 30, 2026, 5:57 p.m.