Triple

T8892813
Position Surface form Disambiguated ID Type / Status
Subject Dreamstreet E211720 entity
Predicate producer P490 FINISHED
Object Jack Rockwell E745719 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 Rockwell | Statement: [Dreamstreet, producer, Jack Rockwell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jack Rockwell
Context triple: [Dreamstreet, producer, Jack Rockwell]
  • A. Jack Rockwell chosen
    Jack Rockwell was an American character actor known for his numerous supporting roles in Western films during the 1930s and 1940s.
  • B. Phil Reeves
    Phil Reeves is an American character actor known for his supporting roles in film and television, including appearances in comedies and dramas such as "13 Going on 30."
  • C. Richard Franklin
    Richard Franklin was a British actor best known for playing Captain Mike Yates in the classic science fiction television series Doctor Who.
  • D. Edward Pawley
    Edward Pawley was an American actor known for his work in 1930s and 1940s films and radio dramas.
  • E. Tom Rothrock
    Tom Rothrock is an American record producer and musician known for his work with artists such as James Blunt, Beck, and Elliott Smith.
  • 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_69ca83907954819096d52a245b635841 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc61bb46c881909e579bb1926e5204 completed April 1, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfabf795b08190bb4c45d6ede3b8b4 completed April 3, 2026, noon
Created at: March 30, 2026, 6:54 p.m.