Triple
T9334261
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Bushmills Distillery |
E224604
|
entity |
| Predicate | whiskeyType |
P14783
|
FINISHED |
| Object | single malt Irish whiskey |
—
|
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: single malt Irish whiskey | Statement: [Old Bushmills Distillery, whiskeyType, single malt Irish whiskey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: whiskeyType Context triple: [Old Bushmills Distillery, whiskeyType, single malt Irish whiskey]
-
A.
distilleryType
Indicates the specific kind or category of distillery associated with an entity (e.g., craft, industrial, micro, or regional type).
-
B.
alcoholType
chosen
Indicates the specific kind or category of alcohol associated with an entity (e.g., beer, wine, spirits).
-
C.
distillationType
Indicates the specific method or process of distillation used to separate or refine substances.
-
D.
beerStyle
Indicates that one entity is the style or type classification of a beer associated with another entity.
-
E.
wineCategory
Indicates the classification or type of wine that an entity (such as a specific wine) belongs to.
- 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_69ca84286fcc81909f6e7fd7a7e862a2 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd37ee53988190bcc76588edbc2858 |
completed | April 1, 2026, 3:21 p.m. |
| PD | Predicate disambiguation | batch_69cc7a643924819097f01144734901cf |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:39 p.m.