Triple
T6613470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madeira wine |
E149290
|
entity |
| Predicate | traditionalAgingMethod |
P14739
|
FINISHED |
| Object | canteiro system |
—
|
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: canteiro system | Statement: [Madeira wine, traditionalAgingMethod, canteiro system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: traditionalAgingMethod Context triple: [Madeira wine, traditionalAgingMethod, canteiro system]
-
A.
traditionalPreparation
Indicates that something is prepared or made using customary, long-established methods or techniques associated with a particular culture or practice.
-
B.
traditionalVinification
chosen
Indicates that a wine is produced using traditional or historically established winemaking methods rather than modern or industrial techniques.
-
C.
typicalAgingTime
Indicates the usual duration required for something to age or mature under normal conditions.
-
D.
traditionalAncestor
Indicates that one entity is regarded as an ancestor of another according to traditional, customary, or culturally transmitted lineage beliefs rather than strictly documented genealogical records.
-
E.
fermentationMethod
Indicates the process or technique by which a substance is fermented to achieve a desired transformation or product.
- 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_69c687ebc680819094caf71faba2efe2 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6cf3796d08190a26e988386089447 |
completed | March 27, 2026, 6:40 p.m. |
| PD | Predicate disambiguation | batch_69c6acfed25481909cac74c84a9fe088 |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 1:57 p.m.