Triple
T5245235
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ardbeg distillery |
E118441
|
entity |
| Predicate | committeeFoundedIn |
P62363
|
FINISHED |
| Object | 2000 |
—
|
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: 2000 | Statement: [Ardbeg distillery, committeeFoundedIn, 2000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: committeeFoundedIn Context triple: [Ardbeg distillery, committeeFoundedIn, 2000]
-
A.
organizationFounded
Indicates that an organization was established or created at a specific point in time, often by a particular founder or founding entity.
-
B.
foundingOrganization
Indicates the organization that established or created another entity, such as a company, institution, or project.
-
C.
foundedOrganization
Indicates that an entity established or created an organization.
-
D.
committeeOfOrigin
Indicates the committee in which a proposal, bill, or item was first introduced or initially considered.
-
E.
foundingLocationOfFoundedOrganization
Indicates the place where an organization was originally established or founded.
- 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.