Triple
T24566361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sercial |
E607800
|
entity |
| Predicate | styleOfMadeira |
P2082
|
FINISHED |
| Object | dry |
—
|
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: dry | Statement: [Sercial, styleOfMadeira, dry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: styleOfMadeira Context triple: [Sercial, styleOfMadeira, dry]
-
A.
distanceFromMadeiraIsland
Indicates the spatial distance between an entity and Madeira Island.
-
B.
isMaritimeStyle
Indicates that something exhibits characteristics or design elements associated with maritime or nautical style.
-
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.
Caldas de Monchique
Indicates a locational or associative relationship involving the place named Caldas de Monchique, such as being situated in, originating from, or otherwise connected to that locality.
-
E.
wineStyleOrigin
Indicates that a particular wine style originated in or is traditionally associated with a specific geographic region or place.
- 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_69e2c4cc35a48190990b7571bc086df8 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a92082a881908896dcdda85559b9 |
completed | April 30, 2026, 12:58 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b99e7c8190ba7e2dc8729a314a |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:28 a.m.