Triple
T9866011
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Burgundy AOC wines |
E239833
|
entity |
| Predicate | typicalWhiteStyleDescriptor |
P90955
|
FINISHED |
| Object | citrus and green apple aromas |
—
|
LITERAL 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: citrus and green apple aromas | Statement: [Burgundy AOC wines, typicalWhiteStyleDescriptor, citrus and green apple aromas]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalWhiteStyleDescriptor Context triple: [Burgundy AOC wines, typicalWhiteStyleDescriptor, citrus and green apple aromas]
-
A.
styleWhite
Indicates that one entity has a white style, appearance, or coloration in relation to another or within a given context.
-
B.
typicalVisualStyle
Indicates the characteristic or commonly observed visual appearance or aesthetic style associated with an entity.
-
C.
typicalColorDescription
Indicates the usual or characteristic color associated with an entity.
-
D.
primaryWhiteVariety
Indicates that one entity is the primary white (light-skinned or white-colored) variety or form of another entity.
-
E.
traditionalStyle
Indicates that something follows or embodies a conventional, long-established way of doing, making, or presenting it, in contrast to modern or innovative styles.
- F. None of above. chosen
Provenance (4 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_69ca84e7506c819095cbde4ff16512bb |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb3d091e48190b10463562d0dc461 |
completed | April 2, 2026, 12:09 a.m. |
| PD | Predicate disambiguation | batch_69cd1d7621d48190aa6a6f34399514b0 |
completed | April 1, 2026, 1:28 p.m. |
| PDg | Predicate description generation | batch_69cd3581a9688190a00cef4c3eebb0ae |
completed | April 1, 2026, 3:10 p.m. |
Created at: March 30, 2026, 8:36 p.m.