Triple
T22007285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lagavulin Distillers Edition |
E543480
|
entity |
| Predicate | secondaryCaskType |
P143411
|
FINISHED |
| Object | fortified wine casks |
—
|
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: fortified wine casks | Statement: [Lagavulin Distillers Edition, secondaryCaskType, fortified wine casks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondaryCaskType Context triple: [Lagavulin Distillers Edition, secondaryCaskType, fortified wine casks]
-
A.
secondaryCup
Indicates that one cup serves as a secondary or backup cup in relation to a primary cup.
-
B.
secondMaturationCask
chosen
Indicates that an entity undergoes a second maturation phase in the specified cask.
-
C.
typicalCaskType
Indicates the usual or most commonly used type of cask associated with a given entity or context.
-
D.
secondaryGrape
Indicates that one grape variety serves as a secondary or supporting component in a wine blend relative to the primary grape.
-
E.
secondaryWine
Indicates a relationship where one wine is designated as a secondary or supporting wine in relation to a primary wine.
- 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_69e11e2db934819095556760c7d85e4d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127a18c1081909d15aa7ed4b725e3 |
completed | April 28, 2026, 9:33 p.m. |
| PD | Predicate disambiguation | batch_69e6f62dc9d88190ae387f145f9528de |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:21 p.m.