Triple

T3829715
Position Surface form Disambiguated ID Type / Status
Subject Franken E88779 entity
Predicate grapeVariety P975 FINISHED
Object Müller-Thurgau E336101 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: Müller-Thurgau | Statement: [Franken, grapeVariety, Müller-Thurgau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Müller-Thurgau
Context triple: [Franken, grapeVariety, Müller-Thurgau]
  • A. Müller-Thurgau chosen
    Müller-Thurgau is a white wine grape variety known for producing light, aromatic wines, particularly in cool-climate regions of Central Europe.
  • B. Riesling
    Riesling is a highly aromatic white wine grape variety known for its vibrant acidity and floral, citrus, and stone-fruit characteristics, used to produce wines ranging from bone-dry to lusciously sweet.
  • C. Zisling
    Zisling is a Hebrew-language surname most notably associated with Israeli politician and kibbutz movement leader Aharon Zisling.
  • D. Chasselas wine
    Chasselas wine is a light, delicate white wine grape variety particularly associated with Swiss vineyards along Lake Geneva, especially in the Lavaux region.
  • E. Seyval blanc
    Seyval blanc is a French hybrid white wine grape known for its citrusy, crisp wines and strong suitability to cool-climate regions such as the American Midwest and Northeast.
  • 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_69aed9538cf881909d9ce8ca4ac7c18c completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeeb8459f881908a2c91bb07e381ef completed March 9, 2026, 3:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb54636c8190a46224e0a8215e26 completed March 14, 2026, 6:08 a.m.
Created at: March 9, 2026, 3:17 p.m.