Triple
T18896924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maker’s Mark Distillery |
E462231
|
entity |
| Predicate | hasTastingNotes |
P69349
|
FINISHED |
| Object | caramel and vanilla notes |
—
|
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: caramel and vanilla notes | Statement: [Maker’s Mark Distillery, hasTastingNotes, caramel and vanilla notes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTastingNotes Context triple: [Maker’s Mark Distillery, hasTastingNotes, caramel and vanilla notes]
-
A.
hasTastingProfile
chosen
Indicates that an entity possesses a specific flavor or sensory profile, typically describing its characteristic tastes and aromas.
-
B.
allowsTastingOf
Indicates that one entity permits another entity to sample or try the taste of something.
-
C.
wineCharacteristic
Indicates a descriptive property or quality attributed to a wine, such as its flavor, aroma, color, or style.
-
D.
hasTasteIntensity
Indicates the degree or strength of taste associated with something.
-
E.
hasTastingRoom
Indicates that an establishment provides a dedicated space where visitors can sample or taste its products on-site.
- 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_69d8dcfd05bc819088903cca13cc2846 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c47f6c948190918ade08bb88f1fd |
completed | April 20, 2026, 6:15 a.m. |
| PD | Predicate disambiguation | batch_69e4a2e27e1481908a8da10b28f07875 |
completed | April 19, 2026, 9:39 a.m. |
Created at: April 10, 2026, 11:58 a.m.