Triple
T5245226
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ardbeg distillery |
E118441
|
entity |
| Predicate | numberOfStills |
P62360
|
FINISHED |
| Object | 2 wash stills |
—
|
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: 2 wash stills | Statement: [Ardbeg distillery, numberOfStills, 2 wash stills]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfStills Context triple: [Ardbeg distillery, numberOfStills, 2 wash stills]
-
A.
filmStripCount
Indicates the number of film strips associated with or contained in a given entity or context.
-
B.
numberOfImagesReturned
Indicates the total count of images that are produced or provided as the result of a query, request, or operation.
-
C.
typicalStillType
Indicates that something represents the usual or characteristic form, style, or configuration that an entity typically has or uses.
-
D.
frontCameraCount
Indicates the number of front-facing cameras associated with an entity.
-
E.
rearCameraCount
Indicates the number of camera units located on the rear side of a device.
- F. None of above. chosen
Provenance (4 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_69bd4468aacc8190a8196f71855cdf4f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7b515edc8190a9db198d4eb1c4f6 |
completed | March 20, 2026, 4:52 p.m. |
| PD | Predicate disambiguation | batch_69bd77c1397c8190a7fd844d7a396e54 |
completed | March 20, 2026, 4:37 p.m. |
| PDg | Predicate description generation | batch_69bd79e9d794819097bb628c603d14af |
completed | March 20, 2026, 4:46 p.m. |
Created at: March 20, 2026, 1:49 p.m.