Triple
T38373717
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nikka Whisky Yoichi Distillery |
E893557
|
entity |
| Predicate | usesStillType |
P195959
|
FINISHED |
| Object | copper pot 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: copper pot stills | Statement: [Nikka Whisky Yoichi Distillery, usesStillType, copper pot stills]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesStillType Context triple: [Nikka Whisky Yoichi Distillery, usesStillType, copper pot stills]
-
A.
usesStills
Indicates that one entity employs or incorporates still images or photographs as part of its content, process, or representation.
-
B.
stillUsedBy
Indicates that something continues to be used or relied upon by another entity at the present time.
-
C.
stillType
Indicates that one entity is a specific type or category of "still" (e.g., a particular kind of stillness, still image, or distillation apparatus).
-
D.
typeOfStills
Indicates that one entity is a specific kind or category of stills (e.g., a particular type or style within the broader class of still images or still photography).
-
E.
usedStage
Indicates that an entity made use of a particular stage or phase within a process, workflow, or lifecycle.
- 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_69f76e4b1f748190a380696a16eae4a2 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fdf5d05cc481909ec9e1b1f0784279 |
completed | May 8, 2026, 2:40 p.m. |
| PD | Predicate disambiguation | batch_69fdf0cdd6948190838864ab3120dfa6 |
completed | May 8, 2026, 2:18 p.m. |
| PDg | Predicate description generation | batch_69fdf5cfa1ec8190b80d887fa1bfb4cf |
completed | May 8, 2026, 2:40 p.m. |
Created at: May 3, 2026, 4:31 p.m.