Triple

T7364267
Position Surface form Disambiguated ID Type / Status
Subject Nicky Arnstein E169826 entity
Predicate relationshipTo P37 FINISHED
Object Fanny Brice E117113 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: Fanny Brice | Statement: [Nicky Arnstein, relationshipTo, Fanny Brice]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fanny Brice
Context triple: [Nicky Arnstein, relationshipTo, Fanny Brice]
  • A. Fanny Brice chosen
    Fanny Brice was an American comedienne, singer, and actress best known as a star of the Ziegfeld Follies and the inspiration for the musical "Funny Girl."
  • B. Sophie Tucker
    Sophie Tucker was a popular early 20th-century American singer, comedian, and vaudeville star known as "The Last of the Red Hot Mamas."
  • C. Gracie Allen
    Gracie Allen was an American comedian and actress best known as the zany, quick-witted partner and wife of George Burns in the classic Burns and Allen comedy team.
  • D. Gertrude Berg
    Gertrude Berg was an American actress, screenwriter, and producer best known as the creator and star of the pioneering radio and television series "The Goldbergs."
  • E. Phyllis Diller
    Phyllis Diller was a pioneering American stand-up comedian and actress known for her eccentric stage persona, self-deprecating humor, and distinctive cackling laugh.
  • 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_69c68a5ade988190885b7175f63b7534 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f1603e1481909fb1dce2c9a7c577 completed March 27, 2026, 9:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69c802b90cc081908b15e61921d15b92 completed March 28, 2026, 4:32 p.m.
Created at: March 27, 2026, 3:06 p.m.