Triple

T20538666
Position Surface form Disambiguated ID Type / Status
Subject Soave E504267 entity
Predicate knownFor P22 FINISHED
Object Soave wine 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: Soave wine | Statement: [Soave, knownFor, Soave wine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soave wine
Context triple: [Soave, knownFor, Soave wine]
  • A. Soave chosen
    Soave is a historic Italian town in the Veneto region, renowned for its medieval castle and as the namesake of a famous white wine.
  • B. Bardolino
    Bardolino is a picturesque Italian town in the Veneto region, renowned for its lakeside setting on Lake Garda and its namesake red wine.
  • C. Sciacchetrà wine
    Sciacchetrà wine is a rare, sweet Italian passito wine made from sun-dried grapes on the steep coastal terraces of the Cinque Terre in Liguria.
  • D. Lambrusco wine
    Lambrusco wine is a lightly sparkling Italian red wine, typically fruity and refreshing, traditionally produced in the Emilia-Romagna region.
  • E. Recioto della Valpolicella wine
    Recioto della Valpolicella wine is a traditional sweet red Italian wine from the Valpolicella region, made from partially dried grapes to produce rich, concentrated flavors.
  • 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_69e0b4b476648190bc6019622ae54d3c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a29006008190aa1ee3224c75ff4b completed April 20, 2026, 10:02 p.m.
Created at: April 16, 2026, 11:37 a.m.