Triple
T17050817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Speyside |
E413688
|
entity |
| Predicate | hasTypicalStyle |
P1609
|
FINISHED |
| Object | light-bodied whisky |
—
|
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: light-bodied whisky | Statement: [Speyside, hasTypicalStyle, light-bodied whisky]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypicalStyle Context triple: [Speyside, hasTypicalStyle, light-bodied whisky]
-
A.
hasStyle
chosen
Indicates that an entity possesses, exhibits, or is characterized by a particular style or manner.
-
B.
hasContractStyle
Indicates that one entity is associated with or characterized by a particular contract style or contractual format.
-
C.
typicalVisualStyle
Indicates the characteristic or commonly observed visual appearance or aesthetic style associated with an entity.
-
D.
hasStationStyle
Indicates that one entity (typically a station) possesses or is characterized by a particular architectural or design style.
-
E.
hasTypicalSleeveStyle
Indicates the usual or characteristic sleeve design associated with an item, such as a garment or uniform.
- 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_69d886cde3d481908d4d01ba88ba7eb7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3daa26e84819098b41ae15618e813 |
completed | April 18, 2026, 7:25 p.m. |
| PD | Predicate disambiguation | batch_69e35d60a588819084f53ef9f8b2e7c0 |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:34 a.m.