Triple

T13392179
Position Surface form Disambiguated ID Type / Status
Subject Eddie Anderson E319601 entity
Predicate workedWith P398 FINISHED
Object Jack Benny E61535 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 Benny | Statement: [Eddie Anderson, workedWith, Jack Benny]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jack Benny
Context triple: [Eddie Anderson, workedWith, Jack Benny]
  • A. Jack Benny chosen
    Jack Benny was a pioneering American comedian, actor, and radio/television star renowned for his masterful timing, stingy persona, and influential deadpan style.
  • B. Fred Allen
    Fred Allen was an American film editor active in mid-20th-century cinema, known for his work on numerous Hollywood productions.
  • C. Fred Allen
    Fred Allen was a prominent American comedian and radio host best known for his witty, satirical radio programs during the 1930s and 1940s.
  • D. Red Skelton
    Red Skelton was a beloved American comedian, actor, and radio and television entertainer best known for his long-running TV variety show and iconic clown characters.
  • E. Milton Berle
    Milton Berle was an American comedian and actor widely known as one of television’s first major stars, often called “Mr. Television” for his pioneering role in early TV entertainment.
  • 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_69d806b886bc8190b676e7768b8e01c5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dba0d74e5881909828854bba7d9a87 completed April 12, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75d84d19081909f564c90b50fda60 completed May 3, 2026, 2:36 p.m.
Created at: April 9, 2026, 9:34 p.m.