Triple
T23102591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Savagnin Blanc |
E576072
|
entity |
| Predicate | usedFor |
P98
|
FINISHED |
| Object | Vin Jaune |
—
|
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: Vin Jaune | Statement: [Savagnin Blanc, usedFor, Vin Jaune]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vin Jaune Context triple: [Savagnin Blanc, usedFor, Vin Jaune]
-
A.
Vin Jaune
chosen
Vin Jaune is a distinctive French white wine from the Jura, known for its oxidative aging under a veil of yeast that gives it nutty, sherry-like aromas and remarkable longevity.
-
B.
Greuze
Greuze is a French surname most famously associated with Jean-Baptiste Greuze, an 18th-century painter known for his sentimental and moralizing genre scenes.
-
C.
Tanguy
Tanguy is a French surname most notably associated with Yves Tanguy, a prominent 20th-century Surrealist painter.
-
D.
Marcelin
Marcelin is a French diminutive form of the given name Marcel, often used as an affectionate or familiar variant.
-
E.
Guy Béart
Guy Béart was a French singer-songwriter and guitarist known for his poetic chansons and influential role in postwar French music.
- 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_69e245c060b48190a9bd61a47a16db17 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18de9fa8c81909fd26ff37173b85b |
completed | April 29, 2026, 4:49 a.m. |
Created at: April 17, 2026, 3:58 p.m.