Triple

T17595033
Position Surface form Disambiguated ID Type / Status
Subject Suburra E428547 entity
Predicate director P255 FINISHED
Object Stefano Sollima 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: Stefano Sollima | Statement: [Suburra, director, Stefano Sollima]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stefano Sollima
Context triple: [Suburra, director, Stefano Sollima]
  • A. Stefano Sollima chosen
    Stefano Sollima is an Italian film and television director known for his gritty crime dramas such as "Gomorrah," "Suburra," and the action thriller "Sicario: Day of the Soldado."
  • B. Sergio Sollima
    Sergio Sollima was an Italian film director best known for his influential contributions to the Spaghetti Western genre, including films like "The Big Gundown" and "Face to Face."
  • C. Alessandro Mazzucchetti
    Alessandro Mazzucchetti was a 19th-century Italian architect known for designing major public buildings, including prominent railway stations.
  • D. Gabriele Muccino
    Gabriele Muccino is an Italian film director known internationally for his emotionally driven dramas, including collaborations with Will Smith.
  • E. Paolo Sorrentino
    Paolo Sorrentino is an acclaimed Italian film director and screenwriter known for his visually sumptuous, introspective dramas such as "The Great Beauty" and "Youth."
  • 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_69d889e1030481909950e140c63255b9 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e469ead59c8190a06519311891af3c completed April 19, 2026, 5:36 a.m.
Created at: April 10, 2026, 5:51 a.m.