Triple

T20287915
Position Surface form Disambiguated ID Type / Status
Subject John Froines E509937 entity
Predicate coDefendantWith P31780 FINISHED
Object Lee Weiner NE NERFINISHED

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: Lee Weiner | Statement: [John Froines, coDefendantWith, Lee Weiner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lee Weiner
Context triple: [John Froines, coDefendantWith, Lee Weiner]
  • A. Lee Weiner chosen
    Lee Weiner is an American political activist best known as one of the Chicago Seven defendants charged with conspiracy and inciting riots during the 1968 Democratic National Convention protests.
  • B. Arnold Manoff
    Arnold Manoff was an American screenwriter who worked in film and television and was blacklisted during the McCarthy era.
  • C. Rob Wasserman
    Rob Wasserman was an American Grammy-winning bassist and composer known for his innovative solo work and collaborations with artists such as Bob Weir, Lou Reed, and Elvis Costello.
  • D. Lou Breslow
    Lou Breslow was an American screenwriter and director best known for his work on Hollywood comedies from the 1930s through the 1950s.
  • E. Larry Brezner
    Larry Brezner was an American film producer and talent manager known for producing popular comedies such as "Good Morning, Vietnam," "The 'Burbs," and "Ride Along."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4c652388190b782cad965e5a098 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6769414488190b38e07fd1e989aba completed April 20, 2026, 6:55 p.m.
Created at: April 16, 2026, 11:09 a.m.