Triple
T31202117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greco di Tufo wine |
E795502
|
entity |
| Predicate | allowedOtherGrapes |
P37246
|
FINISHED |
| Object | Coda di Volpe |
—
|
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: Coda di Volpe | Statement: [Greco di Tufo wine, allowedOtherGrapes, Coda di Volpe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allowedOtherGrapes Context triple: [Greco di Tufo wine, allowedOtherGrapes, Coda di Volpe]
-
A.
maximumOtherGrapesContent
Indicates the highest allowable proportion of grapes from other specified sources or varieties that may be included in a given grape-related product or mixture.
-
B.
grapeVarietyAllowed
chosen
Indicates that a specific grape variety is permitted or authorized for use in a given context, such as a wine, region, or product specification.
-
C.
alsoUsesGrapeVariety
Indicates that one entity, in addition to another, makes use of the same grape variety in its composition or production.
-
D.
forbidsGrape
Indicates that one entity prohibits or does not allow the use, presence, or consumption of grapes in relation to another entity.
-
E.
allowsTastingOf
Indicates that one entity permits another entity to sample or try the taste of something.
- 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_69f224d8c6608190b7882466521f62be |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f7b0e5744c8190a22c1e1d6fcfa466 |
completed | May 3, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f7ab70d034819080295628497d8582 |
completed | May 3, 2026, 8:09 p.m. |
Created at: April 29, 2026, 9:09 p.m.