Triple
T5380911
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Verdelho |
E113078
|
entity |
| Predicate | wineTypeAssociation |
P55208
|
FINISHED |
| Object | fortified wine |
—
|
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: fortified wine | Statement: [Verdelho, wineTypeAssociation, fortified wine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wineTypeAssociation Context triple: [Verdelho, wineTypeAssociation, fortified wine]
-
A.
wineStylesAssociatedWith
chosen
Indicates a relationship where certain wine styles are linked or connected to a particular entity, such as a region, grape, producer, or product.
-
B.
wineStyle
Indicates the stylistic category or type of wine (such as its production style, sweetness, body, or other defining characteristics) associated with an entity.
-
C.
wineCategory
Indicates the classification or type of wine that an entity (such as a specific wine) belongs to.
-
D.
wineStructure
Indicates the overall sensory framework of a wine, encompassing how its components like acidity, tannin, body, and alcohol are balanced and interact.
-
E.
wineClassificationSystem
Indicates a system or scheme used to categorize and organize wines based on defined criteria such as origin, style, or quality.
- 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_69bd4436a1988190af18dcff7fd306b4 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd88801b188190b9ac35ed89167fa3 |
completed | March 20, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69bd846172788190969f24bc7503c05e |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:03 p.m.