Triple

T4622874
Position Surface form Disambiguated ID Type / Status
Subject Three Stooges E101027 entity
Predicate laterMembers P7654 FINISHED
Object Joe Besser E334734 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: Joe Besser | Statement: [Three Stooges, laterMembers, Joe Besser]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joe Besser
Context triple: [Three Stooges, laterMembers, Joe Besser]
  • A. Joe Besser chosen
    Joe Besser was an American comedian and actor best known as one of the later members of The Three Stooges and for his distinctive whiny, childlike persona in film and television.
  • B. Shelley Berman
    Shelley Berman was an American comedian, actor, and writer renowned as a pioneering stand-up performer whose influential comedy albums helped popularize observational humor.
  • C. Edgar Bergen
    Edgar Bergen was a famed American ventriloquist and radio performer best known for his dummy characters Charlie McCarthy and Mortimer Snerd.
  • D. Jack Benny
    Jack Benny was a pioneering American comedian, actor, and radio/television star renowned for his masterful timing, stingy persona, and influential deadpan style.
  • E. Norman I. Badler
    Norman I. Badler is an American computer scientist known for his pioneering work in computer graphics, human modeling, and animation, and for his long tenure as a professor at the University of Pennsylvania.
  • 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_69bd43d0497c8190ac23c65c5804846a completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd6234e8108190b985270b9ddd1f3a completed March 20, 2026, 3:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69be399de7248190ba4cde67ff4cbff4 completed March 21, 2026, 6:24 a.m.
Created at: March 20, 2026, 1:12 p.m.