Triple
T23083454
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arran Single Malt Scotch Whisky |
E575538
|
entity |
| Predicate | ageStatementVariants |
P150867
|
FINISHED |
| Object | no age statement |
—
|
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: no age statement | Statement: [Arran Single Malt Scotch Whisky, ageStatementVariants, no age statement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ageStatementVariants Context triple: [Arran Single Malt Scotch Whisky, ageStatementVariants, no age statement]
-
A.
ageStatement
Indicates that a statement expresses or asserts the age of an entity in terms of time lived or existed.
-
B.
ageVariants
Indicates that one entity is an alternative form or version of another distinguished specifically by age (e.g., younger/older or different life-stage variants).
-
C.
ageType
Indicates the specific categorization or classification of an age value (e.g., actual, estimated, range-based) associated with an entity.
-
D.
ageDetail
Indicates a detailed specification of an entity’s age, such as exact value, range, or related age attributes.
-
E.
ageStatus
Indicates the relationship between an entity and its classification into an age-related category or status (e.g., minor, adult, senior).
- 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_69e245bf3e3c819086d3448720efc01b |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18da304548190ab7a421c1ded0eb6 |
completed | April 29, 2026, 4:48 a.m. |
| PD | Predicate disambiguation | batch_69ef89e5ce748190b2c3ac3843484127 |
completed | April 27, 2026, 4:08 p.m. |
| PDg | Predicate description generation | batch_69ef9b7494f4819088ae59ea3d0ae8ab |
completed | April 27, 2026, 5:23 p.m. |
Created at: April 17, 2026, 3:56 p.m.