Triple

T22749039
Position Surface form Disambiguated ID Type / Status
Subject Francesco de Virgilio E562639 entity
Predicate employer P7 FINISHED
Object Lancia 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: Lancia | Statement: [Francesco de Virgilio, employer, Lancia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lancia
Context triple: [Francesco de Virgilio, employer, Lancia]
  • A. Lancia chosen
    Lancia is an Italian automobile manufacturer renowned for its historic innovations and success in motorsport, particularly rally racing.
  • B. Alfa Romeo
    Alfa Romeo is an Italian automobile manufacturer renowned for its sporty, stylish cars and long heritage in motorsport and performance engineering.
  • C. Lancia Aprilia
    The Lancia Aprilia is an innovative late-1930s Italian family car renowned for its advanced aerodynamics, independent suspension, and pioneering unibody construction.
  • D. Fiat
    Fiat is an Italian automobile manufacturer known for producing compact city cars and mass-market vehicles, now operating as a brand within the multinational automotive group Stellantis.
  • E. Maserati
    Maserati is an Italian luxury automobile manufacturer renowned for its high-performance sports cars and grand tourers distinguished by elegant design and racing heritage.
  • 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_69e24551ec7881909a9c924dbea155f6 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f179b822988190b5368ac1f4e1d70a completed April 29, 2026, 3:23 a.m.
Created at: April 17, 2026, 3:24 p.m.