Triple
T21675102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cannonau di Sardegna |
E534945
|
entity |
| Predicate | typicalVineyardLocation |
P45203
|
FINISHED |
| Object | hillsides |
—
|
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: hillsides | Statement: [Cannonau di Sardegna, typicalVineyardLocation, hillsides]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalVineyardLocation Context triple: [Cannonau di Sardegna, typicalVineyardLocation, hillsides]
-
A.
vineyardLocation
chosen
Indicates the geographical place where a vineyard is situated or established.
-
B.
traditionalVineyardArea
Indicates the area of land that is used as a traditional vineyard, typically cultivated with long-established grape-growing practices.
-
C.
hasVineyardsNear
Indicates that one entity possesses or is associated with vineyards located in close geographic proximity to another entity.
-
D.
viticulturalClimate
Indicates the type of climate conditions relevant to grape growing and wine production that characterize a given region or area.
-
E.
hasVineyards
Indicates that one entity possesses, contains, or is associated with vineyards used for growing grapevines.
- 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_69e0c46898008190aa618a4af55bd1ee |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef8a0ed5388190b8f1932fb3f11c6a |
completed | April 27, 2026, 4:08 p.m. |
| PD | Predicate disambiguation | batch_69e6968abfdc81909cf9e0bd72db9eca |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:41 p.m.