Triple
T30091694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Morellino di Scansano |
E764750
|
entity |
| Predicate | minimumSangioveseContent |
P91947
|
FINISHED |
| Object | 85% |
—
|
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% | Statement: [Morellino di Scansano, minimumSangioveseContent, 85%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: minimumSangioveseContent Context triple: [Morellino di Scansano, minimumSangioveseContent, 85%]
-
A.
maximumSangioveseContent
Indicates the highest allowable proportion or amount of Sangiovese in a given context or product.
-
B.
minimumVernacciaContent
Indicates the required minimum amount or proportion of Vernaccia content that must be present in a given product or mixture.
-
C.
dominantGrapePercentageRequirement
chosen
Indicates the minimum percentage of a single grape variety that must be present in a wine for it to be considered dominant or to meet a specific labeling or classification rule.
-
D.
minimumAlcoholRed
Indicates that there is a specified minimum alcohol content requirement associated with red wine or red alcoholic beverages.
-
E.
minimumMalbecPercentage
Indicates the minimum required percentage of Malbec in a composition, blend, or product for a given rule or classification to apply.
- 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_69f22473c0fc8190a926a8051b3b378b |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f69dfdda708190be290c7bec205445 |
completed | May 3, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69f69d1a37e081908d1d86b90ff502bd |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 7:06 p.m.