Triple

T20070930
Position Surface form Disambiguated ID Type / Status
Subject Franco Scaglione E499734 entity
Predicate employer P7 FINISHED
Object Bertone 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: Bertone | Statement: [Franco Scaglione, employer, Bertone]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bertone
Context triple: [Franco Scaglione, employer, Bertone]
  • A. Bertone chosen
    Bertone is an Italian automotive design and coachbuilding firm renowned for styling numerous iconic European cars.
  • B. Bertone
    Bertone is an Italian surname most notably associated with Tarcisio Bertone, a prominent cardinal and former Vatican Secretary of State.
  • C. Zagato
    Zagato is an Italian automotive design and coachbuilding firm renowned for its lightweight, aerodynamically styled sports and racing cars.
  • D. Carrozzeria Ghia
    Carrozzeria Ghia is an Italian automotive design and coachbuilding firm renowned for its stylish mid-20th-century car designs for various major manufacturers.
  • E. Carrozzeria Frua
    Carrozzeria Frua was an Italian coachbuilding and car design firm renowned for its elegant, bespoke sports and luxury car bodies during the mid-20th century.
  • 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_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6643798a4819081fa4e71c74b47bc completed April 20, 2026, 5:36 p.m.
Created at: April 11, 2026, 3:40 p.m.