Triple

T9206960
Position Surface form Disambiguated ID Type / Status
Subject Charles Fleischer E221005 entity
Predicate voiceRole P12691 FINISHED
Object Benny the Cab E183548 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: Benny the Cab | Statement: [Charles Fleischer, voiceRole, Benny the Cab]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Benny the Cab
Context triple: [Charles Fleischer, voiceRole, Benny the Cab]
  • A. Benny the Cab chosen
    Benny the Cab is a wisecracking, anthropomorphic taxicab character from the live-action/animated film "Who Framed Roger Rabbit."
  • B. Benny
    Benny is a common diminutive form of the given name Benedict, often used as a familiar or affectionate nickname.
  • C. Bennie
    Bennie is a masculine given name, often used as a diminutive of Benjamin or Bennett.
  • D. Nicely-Nicely Johnson
    Nicely-Nicely Johnson is a jovial, comic gambler and sidekick character from the musical "Guys and Dolls," known for the showstopping number "Sit Down, You're Rockin' the Boat."
  • E. Loco Dempsey
    Loco Dempsey is a glamorous, fun-loving fashion model and one of the three gold-digging heroines in the classic 1953 romantic comedy film "How to Marry a Millionaire."
  • 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_69ca83e9d0e081908bdb71097201a06c completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccd9b0b6788190908bee67a0c5d48f completed April 1, 2026, 8:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69d065e49fcc81909ddb838a8ad28c57 completed April 4, 2026, 1:14 a.m.
Created at: March 30, 2026, 7:26 p.m.