Triple

T18957273
Position Surface form Disambiguated ID Type / Status
Subject Curly Howard E463813 entity
Predicate familyName P18 FINISHED
Object Horwitz 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: Horwitz | Statement: [Curly Howard, familyName, Horwitz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Horwitz
Context triple: [Curly Howard, familyName, Horwitz]
  • A. Horwitz
    Horwitz is a German-French actor and singer known for his work in film, television, and theater, particularly in German-language productions.
  • B. Horwitz chosen
    Horwitz is the family surname of Moe Howard, the American comedian best known as the bowl-cut leader of the slapstick trio The Three Stooges.
  • C. Goorwitz
    Goorwitz is the birth surname of American character actor Allen Garfield, who was born Allen Goorwitz.
  • D. Horovitz
    Horovitz is a surname most prominently associated with American playwright and screenwriter Israel Horovitz.
  • E. Orowitz
    Orowitz is the original family surname of American actor, director, and producer Michael Landon, known for his roles in classic television series such as "Bonanza" and "Little House on the Prairie."
  • 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_69d8dcffc278819086792a4ebfddfafa completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d5cee8348190b6506b10aed6c58a completed April 20, 2026, 7:29 a.m.
Created at: April 10, 2026, noon