Triple

T3017506
Position Surface form Disambiguated ID Type / Status
Subject Humoresque E82372 entity
Predicate director P255 FINISHED
Object Jean Negulesco E224479 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: Jean Negulesco | Statement: [Humoresque, director, Jean Negulesco]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jean Negulesco
Context triple: [Humoresque, director, Jean Negulesco]
  • A. Jean Negulesco chosen
    Jean Negulesco was a Romanian-American film director and screenwriter best known for his stylish Hollywood dramas and romances from the 1940s and 1950s.
  • B. Gregory La Cava
    Gregory La Cava was an American film director best known for his sophisticated 1930s comedies and character-driven dramas in Hollywood’s Golden Age.
  • C. Leo Tover
    Leo Tover was an American cinematographer known for his work on numerous classic Hollywood films across several decades.
  • D. Emile Ardolino
    Emile Ardolino was an American film director best known for popular hits like "Dirty Dancing" and "Sister Act," as well as his work on dance-focused documentaries.
  • E. George Jessel
    George Jessel was an American actor, comedian, and film producer known as "The Toastmaster General of the United States" for his prolific work in entertainment and public speaking.
  • 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_69ad8b1eb53481908c39bbcd1ec104b2 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9a90ea64819080620e60bbd6aa24 completed March 8, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b12e6eac1481909d56844e53c37b59 completed March 11, 2026, 8:57 a.m.
Created at: March 8, 2026, 3 p.m.