Triple

T16013574
Position Surface form Disambiguated ID Type / Status
Subject Lori Martin E388402 entity
Predicate coStarredWith P14987 FINISHED
Object Robert Mitchum E251971 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: Robert Mitchum | Statement: [Lori Martin, coStarredWith, Robert Mitchum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Mitchum
Context triple: [Lori Martin, coStarredWith, Robert Mitchum]
  • A. Robert Mitchum chosen
    Robert Mitchum was an American film actor renowned for his tough, laconic screen persona in classic noir, Western, and war films from the 1940s through the 1970s.
  • B. John Mitchum
    John Mitchum was an American character actor and writer, known for his supporting roles in film and television and for being part of the Mitchum acting family.
  • C. Glenn Ford
    Glenn Ford was a Canadian-American film actor renowned for his versatile performances in classic Hollywood movies such as "Gilda," "The Big Heat," and "Blackboard Jungle."
  • D. James Mitchum
    James Mitchum is an American actor and the eldest son of legendary film star Robert Mitchum, known for appearing in several films from the 1950s onward.
  • E. Ray Taylor
    Ray Taylor was an American film director best known for his work on action-packed serials and B-movies during the early 20th century.
  • 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_69d86dabcb7c8190b6a39d6831d2fa1b completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e18292b79881908efac869603c4029 completed April 17, 2026, 12:45 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00b274fa3481908b019036cd2ae627 completed May 10, 2026, 4:29 p.m.
Created at: April 10, 2026, 4:55 a.m.