Triple

T22581502
Position Surface form Disambiguated ID Type / Status
Subject Mamma Roma E544578 entity
Predicate musicBy P1952 FINISHED
Object Carlo Rustichelli 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 Rustichelli | Statement: [Mamma Roma, musicBy, Carlo Rustichelli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carlo Rustichelli
Context triple: [Mamma Roma, musicBy, Carlo Rustichelli]
  • A. Carlo Rustichelli chosen
    Carlo Rustichelli was an Italian film composer renowned for his prolific work scoring classic Italian and international movies throughout the mid-20th century.
  • B. Alcide De Gasperi
    Alcide De Gasperi was an Italian statesman and founding father of the Italian Republic who served as its post–World War II prime minister and a key architect of European integration.
  • C. Luigi Bonomi
    Luigi Bonomi is a prominent British literary agent known for representing bestselling commercial and genre fiction authors.
  • D. Ciriaco De Mita
    Ciriaco De Mita was an Italian Christian Democrat politician who served as Prime Minister of Italy in the late 1980s and was a key figure in postwar Italian coalition politics.
  • E. Romano Artioli
    Romano Artioli is an Italian entrepreneur best known for reviving the Bugatti brand in the late 20th century and serving as its president during the EB110 era.
  • 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_69e11e30d05481909df915354c89f0d6 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f15ff13e288190b5e4b527470be75e completed April 29, 2026, 1:33 a.m.
Created at: April 16, 2026, 8:53 p.m.