Triple

T20284511
Position Surface form Disambiguated ID Type / Status
Subject The Ghosts of Versailles E509841 entity
Predicate character P662 FINISHED
Object Figaro 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: Figaro | Statement: [The Ghosts of Versailles, character, Figaro]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Figaro
Context triple: [The Ghosts of Versailles, character, Figaro]
  • A. Figaro
    Figaro is a production company known for its work on the cooking and lifestyle television series "The Barefoot Contessa."
  • B. Figaro chosen
    Figaro is the clever, quick-witted barber who serves as the central character in Beaumarchais’s plays and later in Rossini’s opera "The Barber of Seville."
  • C. Figaro
    Figaro is the playful black-and-white kitten from Disney’s classic animated films, best known as a companion to characters like Geppetto and Minnie Mouse.
  • D. Figaro
    "Figaro" is a critically acclaimed track by the hip-hop duo Madvillain (MF DOOM and Madlib), known for its intricate wordplay and distinctive production.
  • E. Schaunard
    Schaunard is a lively and eccentric musician who is one of the four bohemian friends in Giacomo Puccini’s opera *La Bohème*.
  • 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_69e0b4c652388190b782cad965e5a098 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e67691516c81909f32b176edb6214c completed April 20, 2026, 6:55 p.m.
Created at: April 16, 2026, 11:05 a.m.