Triple
T22243685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Slane Distillery |
E549786
|
entity |
| Predicate | typeOfWhiskeyProduced |
P131858
|
FINISHED |
| Object | blended 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: blended Irish whiskey | Statement: [Slane Distillery, typeOfWhiskeyProduced, blended Irish whiskey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfWhiskeyProduced Context triple: [Slane Distillery, typeOfWhiskeyProduced, blended Irish whiskey]
-
A.
styleOfWhisky
chosen
Indicates the specific style or type category that a whisky belongs to (e.g., single malt, blended, bourbon).
-
B.
distilleryType
Indicates the specific kind or category of distillery associated with an entity (e.g., craft, industrial, micro, or regional type).
-
C.
recognizesAsBestWhisky
Indicates that one entity regards another whisky as the best among a relevant set or category.
-
D.
firstWhiskyReleased
Indicates that the subject is the entity whose first whisky was released on the specified date or in the specified release event.
-
E.
alcoholType
Indicates the specific kind or category of alcohol associated with an entity (e.g., beer, wine, spirits).
- 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_69e11e41d9408190bd770cf282e22753 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1321655b0819091f1ddf06c67f3c2 |
completed | April 28, 2026, 10:17 p.m. |
| PD | Predicate disambiguation | batch_69e72fe1e0cc8190bd13cff2a0846225 |
completed | April 21, 2026, 8:05 a.m. |
Created at: April 16, 2026, 8:38 p.m.