Triple
T6885302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kardenakhi |
E158902
|
entity |
| Predicate | wineProductionMethod |
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: [Kardenakhi, wineProductionMethod, qvevri fermentation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wineProductionMethod Context triple: [Kardenakhi, wineProductionMethod, qvevri fermentation]
-
A.
traditionalVinification
Indicates that a wine is produced using traditional or historically established winemaking methods rather than modern or industrial techniques.
-
B.
producesWine
Indicates that one entity creates or manufactures wine as a product.
-
C.
sparklingWineMethod
Indicates that a wine is produced using a specific method or process for making sparkling wine.
-
D.
vinification
chosen
Indicates the process by which grapes (or other fruits) are transformed into wine through fermentation and related winemaking steps.
-
E.
hasWineMakingTradition
Indicates that a place or group has an established, culturally recognized history and practice of producing wine.
- 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_69c688342f6c8190ad7eea6ba262db99 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d90bc32c8190baf5bf785146f3e8 |
completed | March 27, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69c6d7b53e9881909ec298daa9f1913b |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:23 p.m.