Triple
T26748254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Côtes de Provence AOC |
E674460
|
entity |
| Predicate | mainProduction |
P165053
|
FINISHED |
| Object | rosé 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: rosé wine | Statement: [Côtes de Provence AOC, mainProduction, rosé wine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainProduction Context triple: [Côtes de Provence AOC, mainProduction, rosé wine]
-
A.
mainProductionState
Indicates the primary state or region where the production of something (e.g., a product, work, or content) predominantly takes place.
-
B.
fromProduction
Indicates that something originates from, is derived from, or is produced by a particular production process, source, or facility.
-
C.
inProduction
Indicates that something is currently being created, manufactured, or developed but is not yet completed or released.
-
D.
currentProduction
Indicates that an entity is presently engaged in producing, manufacturing, or generating another entity or output.
-
E.
targetProduction
Indicates a relationship where one entity is the intended or designated output, result, or product generated by another entity or process.
- F. None of above. chosen
Provenance (4 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_69eecda63a3881908095c47900692e65 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f65705a3048190a3728b695ba2ae65 |
completed | May 2, 2026, 7:56 p.m. |
| PD | Predicate disambiguation | batch_69f651a731508190bb0c8c2462eba224 |
completed | May 2, 2026, 7:33 p.m. |
| PDg | Predicate description generation | batch_69f6562ef4e4819082ce6abd41b74dc5 |
completed | May 2, 2026, 7:53 p.m. |
Created at: April 27, 2026, 3:52 a.m.