Triple
T5503540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kisi |
E144382
|
entity |
| Predicate | vinificationMethod |
P14224
|
FINISHED |
| Object | qvevri 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: qvevri fermentation | Statement: [Kisi, vinificationMethod, qvevri fermentation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vinificationMethod Context triple: [Kisi, vinificationMethod, qvevri fermentation]
-
A.
vinification
chosen
Indicates the process by which grapes (or other fruits) are transformed into wine through fermentation and related winemaking steps.
-
B.
traditionalVinification
Indicates that a wine is produced using traditional or historically established winemaking methods rather than modern or industrial techniques.
-
C.
commonVinificationGoal
Indicates that two or more vinification processes share the same intended winemaking objective or outcome.
-
D.
sparklingWineMethod
Indicates that a wine is produced using a specific method or process for making sparkling wine.
-
E.
fermentationMethod
Indicates the process or technique by which a substance is fermented to achieve a desired transformation or product.
- 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_69c008f6b5048190a09064116062cf69 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c01f0bbea48190bb6fecaee9c0b1d0 |
completed | March 22, 2026, 4:55 p.m. |
| PD | Predicate disambiguation | batch_69c01b07bde08190b3933b96bdc70dd5 |
completed | March 22, 2026, 4:38 p.m. |
Created at: March 22, 2026, 3:32 p.m.