Triple
T10330935
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clairette de Die wine |
E242869
|
entity |
| Predicate | carbonationRetention |
P84042
|
FINISHED |
| Object | bottle fermentation |
—
|
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: bottle fermentation | Statement: [Clairette de Die wine, carbonationRetention, bottle fermentation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: carbonationRetention Context triple: [Clairette de Die wine, carbonationRetention, bottle fermentation]
-
A.
carbonation
Indicates that a substance, typically a beverage, has been infused with carbon dioxide gas, resulting in bubbles or fizziness.
-
B.
carbonationDescription
chosen
Indicates the description of the level, style, or characteristics of carbonation present in a beverage.
-
C.
airRetention
Indicates that an entity maintains or preserves air within a space or structure without significant loss.
-
D.
hasCarbonatedWater
Indicates that an entity contains or is associated with carbonated (fizzy) water as a component or ingredient.
-
E.
waterRetention
Indicates the capacity of something to hold or retain water over time.
- F. None of above.
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_69d381af787481908bc401325c760a88 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d7fb77348190ac8ff887f6f03450 |
completed | April 7, 2026, 10:10 a.m. |
| PD | Predicate disambiguation | batch_69d4d1f760e88190abea6dcc4f04f2c1 |
completed | April 7, 2026, 9:44 a.m. |
Created at: April 6, 2026, 11:52 a.m.