Triple
T37625522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evan Williams Black Label |
E936195
|
entity |
| Predicate | commonCocktailUse |
P76750
|
FINISHED |
| Object | Old Fashioned |
—
|
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: Old Fashioned | Statement: [Evan Williams Black Label, commonCocktailUse, Old Fashioned]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commonCocktailUse Context triple: [Evan Williams Black Label, commonCocktailUse, Old Fashioned]
-
A.
commonCocktail
chosen
Indicates that the related entities are ingredients or components that commonly appear together in the same cocktail.
-
B.
notableCocktailUse
Indicates that something is significantly or famously used as an ingredient or component in a particular cocktail.
-
C.
relatedCocktail
Indicates that one cocktail has a meaningful connection or association with another cocktail, such as similarity in ingredients, style, or origin.
-
D.
popularCocktailAssociation
Indicates a relationship where a cocktail is commonly recognized, favored, or widely ordered within a particular group, context, or time period.
-
E.
includesCocktail
Indicates that one entity (such as a menu, list, or collection) contains or features a specific cocktail as part of its contents.
- 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_69f76ed24820819081bafd36e9088701 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff5f5ecc808190b2df364da108ff4c |
completed | May 9, 2026, 4:22 p.m. |
| PD | Predicate disambiguation | batch_69ff5b84131c8190bf81d7fb53e934bc |
completed | May 9, 2026, 4:06 p.m. |
Created at: May 3, 2026, 4:18 p.m.