Triple

T2261614
Position Surface form Disambiguated ID Type / Status
Subject Muscadelle E50051 entity
Predicate usedIn P98 FINISHED
Object Sauternes wines E52047 NE FINISHED

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: Sauternes wines | Statement: [Muscadelle, usedIn, Sauternes wines]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sauternes wines
Context triple: [Muscadelle, usedIn, Sauternes wines]
  • A. Sauternes chosen
    Sauternes is a renowned sweet white wine appellation in southwestern France, famous for its botrytized wines made primarily from Sémillon and Sauvignon Blanc grapes.
  • B. Les Vins de France
    Les Vins de France is a wine-focused retail shop located in the France Pavilion, offering a curated selection of French wines and related products.
  • C. Burgundy AOC wines
    Burgundy AOC wines are French appellation-controlled wines from the Burgundy region, renowned for their terroir-driven expressions of Pinot Noir and Chardonnay across a hierarchy of quality levels.
  • D. Sancerre
    Sancerre is a renowned French wine appellation in the Loire Valley, best known for its crisp, mineral-driven white wines.
  • E. Clairette de Die wine
    Clairette de Die wine is a lightly sparkling, sweet white AOC wine from the Drôme region of France, traditionally made from Muscat and Clairette grapes using an ancestral method.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a88b01e0048190ba96431b5f990ba9 completed March 4, 2026, 7:41 p.m.
NER Named-entity recognition batch_69abc18aa9d48190893ca32558730e9c completed March 7, 2026, 6:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae89477bb481908ce66fac62181f1f completed March 9, 2026, 8:48 a.m.
Created at: March 4, 2026, 7:48 p.m.