Triple

T20774560
Position Surface form Disambiguated ID Type / Status
Subject Christian De Sica E511320 entity
Predicate relative P37 FINISHED
Object Carlo Verdone 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: Carlo Verdone | Statement: [Christian De Sica, relative, Carlo Verdone]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carlo Verdone
Context triple: [Christian De Sica, relative, Carlo Verdone]
  • A. Carlo Verdone chosen
    Carlo Verdone is an Italian film director, screenwriter, and actor known for his acclaimed comedic and dramatic roles in contemporary Italian cinema.
  • B. Adolfo Celi
    Adolfo Celi was an Italian actor and director best known internationally for his roles as suave, often villainous characters in films such as the James Bond movie "Thunderball."
  • C. Vittorio Gassman
    Vittorio Gassman was a renowned Italian actor and director celebrated for his powerful stage work and acclaimed performances in classic Italian cinema.
  • D. Jacopo Gassman
    Jacopo Gassman is an Italian theater director and actor, known both for his stage work and as the son of celebrated actor Vittorio Gassman.
  • E. Gabriele Ferzetti
    Gabriele Ferzetti was an Italian film and stage actor known for his prolific career in European cinema, including prominent roles in classics like "L'Avventura" and the James Bond film "On Her Majesty's Secret Service."
  • 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_69e0b4ca01148190ac018e57e0cab46f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c26a39bc81909ca5d102056d8586 completed April 21, 2026, 12:18 a.m.
Created at: April 16, 2026, 12:37 p.m.