Triple

T16766023
Position Surface form Disambiguated ID Type / Status
Subject Rust E407464 entity
Predicate knownFor P22 FINISHED
Object Ausbruch wine E1143474 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: Ausbruch wine | Statement: [Rust, knownFor, Ausbruch wine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ausbruch wine
Context triple: [Rust, knownFor, Ausbruch wine]
  • A. Ruster Ausbruch wine chosen
    Ruster Ausbruch wine is a renowned Austrian sweet dessert wine made from botrytized grapes around the town of Rust in Burgenland, prized for its richness and complexity.
  • B. Cartojal wine
    Cartojal wine is a sweet, chilled Málaga wine especially popular during the Málaga Fair and associated with festive summer celebrations in southern Spain.
  • C. Ripaille wine
    Ripaille wine is a French white wine from the Chablais region of Savoie, produced from vineyards surrounding the historic Château de Ripaille on the shores of Lake Geneva.
  • D. Robola wine
    Robola wine is a crisp, aromatic white wine from the Greek island of Kefalonia, known for its citrusy minerality and vibrant acidity.
  • E. Barbera wine
    Barbera wine is a deeply colored, high-acid red wine grape variety from Italy’s Piedmont region, widely used to produce vibrant, food-friendly wines.
  • 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_69d8839174188190909f190097207065 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b0330d6081908ce99f14c70b90f2 completed April 18, 2026, 4:24 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a531ea7c81908630f16f6c685d49 completed May 10, 2026, 3:33 p.m.
Created at: April 10, 2026, 5:21 a.m.