Triple

T13338561
Position Surface form Disambiguated ID Type / Status
Subject The Dark Corner E317761 entity
Predicate producer P490 FINISHED
Object Fred Kohlmar E496320 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: Fred Kohlmar | Statement: [The Dark Corner, producer, Fred Kohlmar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fred Kohlmar
Context triple: [The Dark Corner, producer, Fred Kohlmar]
  • A. Fred Kohlmar chosen
    Fred Kohlmar was an American film producer active during Hollywood's studio era, known for overseeing a variety of popular comedies and musicals.
  • B. William Diehl
    William Diehl was an American novelist best known for his gritty, suspenseful legal and crime thrillers.
  • C. Paul W. Kiefer
    Paul W. Kiefer was an American engineer and industrialist best known for his pioneering role in developing diesel-electric locomotive technology and helping shape modern railroad motive power.
  • D. Richard M. Schulze
    Richard M. Schulze is an American businessman and billionaire best known as the founder and longtime leader of the consumer electronics retail chain Best Buy.
  • E. William Steinkamp
    William Steinkamp is an American film editor known for his long-time collaboration with director Sydney Pollack and his work on several acclaimed Hollywood films.
  • 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_69d806b5a3c08190b42c267fb092f98a completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d99d01bf8481908cd3a99e5557b972 completed April 11, 2026, 12:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe8bba60c8819087b614cea03eb078 completed May 9, 2026, 1:19 a.m.
Created at: April 9, 2026, 9:31 p.m.