Triple
T6809603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jura whisky distillery |
E156595
|
entity |
| Predicate | distillation |
P62359
|
FINISHED |
| Object | double distillation |
—
|
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: double distillation | Statement: [Jura whisky distillery, distillation, double distillation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distillation Context triple: [Jura whisky distillery, distillation, double distillation]
-
A.
distillationType
chosen
Indicates the specific method or process of distillation used to separate or refine substances.
-
B.
distilleryType
Indicates the specific kind or category of distillery associated with an entity (e.g., craft, industrial, micro, or regional type).
-
C.
hasDistillery
Indicates that one entity owns, operates, or is associated with a distillery as a facility or production site.
-
D.
maximumDistillationStrength
Indicates the highest concentration or strength that can be achieved through a distillation process.
-
E.
vinification
Indicates the process by which grapes (or other fruits) are transformed into wine through fermentation and related winemaking steps.
- 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_69c68828b26c819090fe9df7612bbc27 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d30c741881909e220b05aa564bc2 |
completed | March 27, 2026, 6:57 p.m. |
| PD | Predicate disambiguation | batch_69c6d099bf08819089a9f9894d037e74 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:16 p.m.