Triple
T20781074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port Ellen Distillery |
E511480
|
entity |
| Predicate | maltingsSupply |
P141521
|
FINISHED |
| Object | multiple Islay distilleries |
—
|
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: multiple Islay distilleries | Statement: [Port Ellen Distillery, maltingsSupply, multiple Islay distilleries]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maltingsSupply Context triple: [Port Ellen Distillery, maltingsSupply, multiple Islay distilleries]
-
A.
typeOfMalt
Indicates the specific kind or category of malt used or referenced in relation to another entity.
-
B.
hasMashBill
Indicates that an alcoholic beverage (typically a spirit like whiskey or bourbon) is produced using a specific mixture of grains (the mash bill).
-
C.
breweryType
Indicates the specific category or classification of a brewery based on its operational or business characteristics.
-
D.
breweryRelation
Indicates a relationship in which one entity is a brewery associated with, producing for, or otherwise linked to another entity (such as a brand, product, or location).
-
E.
isMassMarketBeer
Indicates that a beer is produced and distributed on a large commercial scale for broad, mainstream consumer markets.
- 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_69e0b4cac7a48190a715cb3d545df2b4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c287b5288190823766fe59402d48 |
completed | April 21, 2026, 12:19 a.m. |
| PD | Predicate disambiguation | batch_69e5c0550ec481908a0877fb2409d983 |
completed | April 20, 2026, 5:57 a.m. |
| PDg | Predicate description generation | batch_69e5c3cbe5788190b7ace43bfdac2ef6 |
completed | April 20, 2026, 6:12 a.m. |
Created at: April 16, 2026, 12:37 p.m.