Triple
T31176299
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fiano di Avellino wine |
E794758
|
entity |
| Predicate | minimumFianoContent |
P172951
|
FINISHED |
| Object | 85 percent Fiano grapes |
—
|
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: 85 percent Fiano grapes | Statement: [Fiano di Avellino wine, minimumFianoContent, 85 percent Fiano grapes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: minimumFianoContent Context triple: [Fiano di Avellino wine, minimumFianoContent, 85 percent Fiano grapes]
-
A.
minimumPrimitivoContent
Indicates that there is a specified minimum amount or level of primitive content required in the relationship between the involved entities.
-
B.
minimumVernacciaContent
Indicates the required minimum amount or proportion of Vernaccia content that must be present in a given product or mixture.
-
C.
minimumMass
Indicates the smallest mass value that an entity or system is required, allowed, or observed to have within a given context.
-
D.
minimumBottlingStrength
Indicates the lowest alcohol strength at which a beverage is allowed or intended to be bottled.
-
E.
minimumSize
Indicates that there is a lower bound or smallest allowable value for the size of something in the relationship.
- F. None of above. chosen
Provenance (4 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_69f224d5b9708190b6ca79ad2fd3a28a |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6b2d9aad88190a445f8f591cb19fc |
completed | May 3, 2026, 2:28 a.m. |
| PD | Predicate disambiguation | batch_69f6b14faf608190a25b977c0740729c |
completed | May 3, 2026, 2:22 a.m. |
| PDg | Predicate description generation | batch_69f6b21da77081908c5c015c4606d344 |
completed | May 3, 2026, 2:25 a.m. |
Created at: April 29, 2026, 9:08 p.m.