Triple
T18573280
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Béarn AOC |
E453923
|
entity |
| Predicate | grapeVarietyUsed |
P975
|
FINISHED |
| Object | Gros Manseng |
—
|
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: Gros Manseng | Statement: [Béarn AOC, grapeVarietyUsed, Gros Manseng]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gros Manseng Context triple: [Béarn AOC, grapeVarietyUsed, Gros Manseng]
-
A.
Gros Manseng
chosen
Gros Manseng is a white grape variety from southwest France, best known for producing aromatic, high-acidity wines ranging from dry to lusciously sweet.
-
B.
Muscadelle
Muscadelle is a white wine grape variety known for producing aromatic, floral wines, particularly in regions like Bordeaux where it is often blended with other grapes.
-
C.
Pinot d’Aunis
Pinot d’Aunis is a historic, light-bodied French red grape variety from the Loire Valley, known for producing pale, peppery, and delicately aromatic wines.
-
D.
Marsanne
Marsanne is a white wine grape variety from France’s Rhône Valley, known for producing full-bodied, aromatic wines often blended with Roussanne.
-
E.
Marsanne
Marsanne is a commune in the Drôme department of southeastern France, known for its historic village setting amid the Rhône Valley countryside.
- 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_69d8d38974308190a9174430ef256b73 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e543c7f63c81909b5d5764ffd20234 |
completed | April 19, 2026, 9:06 p.m. |
Created at: April 10, 2026, 11:43 a.m.