Triple
T34558511
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarragona DO |
E887273
|
entity |
| Predicate | typicalWine |
P2082
|
FINISHED |
| Object | young red wines |
—
|
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: young red wines | Statement: [Tarragona DO, typicalWine, young red wines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalWine Context triple: [Tarragona DO, typicalWine, young red wines]
-
A.
notableWine
Indicates that a wine is recognized as significant, distinguished, or noteworthy in some context (such as quality, reputation, or historical importance).
-
B.
traditionalWineChoice
Indicates that an entity selects or prefers a wine option that aligns with customary or historically established pairing or serving practices.
-
C.
wineStyle
chosen
Indicates the stylistic category or type of wine (such as its production style, sweetness, body, or other defining characteristics) associated with an entity.
-
D.
wineVariety
Indicates the specific type or variety of wine associated with an entity.
-
E.
wineCategory
Indicates the classification or type of wine that an entity (such as a specific wine) belongs to.
- 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_69f349d0c4d881908dd0950f5eb9ec0a |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379fd7aac8190873077e63873aa72 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 2:02 a.m.