Triple

T19607043
Position Surface form Disambiguated ID Type / Status
Subject Copacabana (At the Copa) E470633 entity
Predicate writer P1360 FINISHED
Object Jack Feldman 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: Jack Feldman | Statement: [Copacabana (At the Copa), writer, Jack Feldman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jack Feldman
Context triple: [Copacabana (At the Copa), writer, Jack Feldman]
  • A. Jack Feldman chosen
    Jack Feldman is an American lyricist best known for his work on the Disney film and stage musical "Newsies," as well as numerous pop songs and television projects.
  • B. Jon Feldman
    Jon Feldman is an American television writer and producer known for his work on various drama series.
  • C. Jerry Feldman
    Jerry Feldman is the fast-talking, compulsive gambler protagonist of the 1982 comedy film "Lookin' to Get Out," whose misadventures in Las Vegas drive the movie’s plot.
  • D. Michael Feldman
    Michael Feldman is an American political and communications strategist best known as the husband of television journalist Savannah Guthrie.
  • E. Jerome Feldman
    Jerome Feldman is a cognitive scientist and computer scientist known for his contributions to neural networks, computational models of cognition, and the foundations of cognitive science.
  • 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_69d8e510024481908415c0d616fa6186 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e640c8aae8819086337e364724f1cb completed April 20, 2026, 3:05 p.m.
Created at: April 10, 2026, 1:43 p.m.