Triple

T22051721
Position Surface form Disambiguated ID Type / Status
Subject Cinema Paradiso E544900 entity
Predicate stars P1956 FINISHED
Object Marco Leonardi 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: Marco Leonardi | Statement: [Cinema Paradiso, stars, Marco Leonardi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marco Leonardi
Context triple: [Cinema Paradiso, stars, Marco Leonardi]
  • A. Marco Leonardi chosen
    Marco Leonardi is an Italian actor known for his roles in films such as "Cinema Paradiso," "Like Water for Chocolate," and various international productions.
  • B. Marco Brambilla
    Marco Brambilla is an Italian-Canadian visual artist and filmmaker known for his elaborate video collages and for directing the sci-fi action film "Demolition Man."
  • C. Marco Carducci
    Marco Carducci is a Canadian professional soccer goalkeeper known for his standout performances in the Canadian Premier League and recognition as one of the league’s top shot-stoppers.
  • D. Luca Ferraro
    Luca Ferraro is an individual notable enough to be recognized as a prominent bearer of the surname Ferraro.
  • E. Alessio Romenzi
    Alessio Romenzi is an Italian photojournalist known for his powerful coverage of conflicts and humanitarian crises in the Middle East.
  • 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_69e11e32445c8190ab97089b48a130bb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1285513fc8190b691e1f57085956f completed April 28, 2026, 9:36 p.m.
Created at: April 16, 2026, 8:26 p.m.