Triple

T17849625
Position Surface form Disambiguated ID Type / Status
Subject Craig Alpert E445761 entity
Predicate workedWith P398 FINISHED
Object Larry Charles 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: Larry Charles | Statement: [Craig Alpert, workedWith, Larry Charles]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Larry Charles
Context triple: [Craig Alpert, workedWith, Larry Charles]
  • A. Larry Charles chosen
    Larry Charles is an American writer, director, and producer best known for his work on Seinfeld and his collaborations with Sacha Baron Cohen on films like Borat and Brüno.
  • B. Robert Cohl
    Robert Cohl is the son of Canadian film producer and Toronto International Film Festival co-founder Dusty Cohl.
  • C. Louis Stern
    Louis Stern was an early 20th-century film actor who appeared in silent-era productions, including the 1918 drama "Eye for Eye."
  • D. Eric Darnell
    Eric Darnell is an American director, screenwriter, and animator best known for his work on DreamWorks Animation films, including the Madagascar franchise and its spin-offs.
  • E. Vincent Lopez
    Vincent Lopez is an American drummer best known as an original member of Bruce Springsteen’s E Street Band.
  • 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_69d8b9f26f18819089c9e43250bee6ae completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e48ffd7e2c81909a42cc7ab64e7db9 completed April 19, 2026, 8:19 a.m.
Created at: April 10, 2026, 10:16 a.m.