Triple

T9987664
Position Surface form Disambiguated ID Type / Status
Subject Blue Velvet E196809 entity
Predicate castMember P1668 FINISHED
Object Jack Nance E811366 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: Jack Nance | Statement: [Blue Velvet, castMember, Jack Nance]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jack Nance
Context triple: [Blue Velvet, castMember, Jack Nance]
  • A. Jack Nance chosen
    Jack Nance was an American character actor best known for his longtime collaboration with director David Lynch, including his iconic lead role in the cult film "Eraserhead."
  • B. Dale Robertson
    Dale Robertson was an American actor best known for his rugged leading roles in Western films and television series during the 1950s and 1960s.
  • C. James Coburn
    James Coburn was an American actor known for his cool, tough-guy persona in films such as "The Magnificent Seven" and "Our Man Flint," and for winning an Academy Award for his supporting role in "Affliction."
  • D. Randolph Scott
    Randolph Scott was a prominent American film actor best known for his roles in Westerns during the 1930s–1950s.
  • E. David Wayne
    David Wayne was an American character actor known for his versatile performances in film, television, and theater from the 1940s through the 1980s.
  • 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_69ca82f1678c819093d06320a05f16a4 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdc79c8b80819091dc16ac8fd0c720 completed April 2, 2026, 1:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69d25810584c81908382cf6edd700530 completed April 5, 2026, 12:39 p.m.
Created at: March 30, 2026, 8:50 p.m.