Triple

T20015091
Position Surface form Disambiguated ID Type / Status
Subject Romanza E494695 entity
Predicate producer P490 FINISHED
Object Francesco Sartori 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: Francesco Sartori | Statement: [Romanza, producer, Francesco Sartori]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Francesco Sartori
Context triple: [Romanza, producer, Francesco Sartori]
  • A. Francesco Sartori chosen
    Francesco Sartori is an Italian composer best known for writing the music to the internationally acclaimed Andrea Bocelli hit "Con te partirò" ("Time to Say Goodbye").
  • B. 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.
  • C. Ruggero Bonomi
    Ruggero Bonomi was an Italian military officer best known for leading Italian air operations in support of Franco’s forces during the Spanish Civil War.
  • D. Carlo Vittadini
    Carlo Vittadini was a 19th-century Italian physician and mycologist renowned for his pioneering taxonomic studies of truffles and other fungi.
  • E. Araldo Cossutta
    Araldo Cossutta was a Yugoslav-born American architect known for his modernist designs and his work with I. M. Pei on prominent institutional and civic buildings.
  • 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_69da626bfd288190aa5d65098b6433ae completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6623bba1881908440c92f08729ec1 completed April 20, 2026, 5:28 p.m.
Created at: April 11, 2026, 3:34 p.m.