Triple
T18486128
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aberfeldy Distillery |
E451694
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Thomas Dewar |
—
|
NE NERFINISHED |
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: Thomas Dewar | Statement: [Aberfeldy Distillery, foundedBy, Thomas Dewar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Dewar Context triple: [Aberfeldy Distillery, foundedBy, Thomas Dewar]
-
A.
Thomas Dewar
chosen
Thomas Dewar was a prominent Scottish whisky distiller and businessman, best known for co-founding the Dewar’s Scotch whisky brand and helping popularize blended Scotch worldwide.
-
B.
John Dewar
John Dewar is a Scottish whisky distiller best known for founding the Dewar’s blended Scotch whisky brand.
-
C.
Kenneth Dewar
Kenneth Dewar was a British Royal Navy officer and naval historian known for his controversial views on naval tactics and his involvement in interwar naval debates.
-
D.
George Dewar
George Dewar is a person associated with the use or application of the Dewar vessel, commonly linked to scientific or technical contexts.
-
E.
John MacInnes
John MacInnes was a highly successful and influential college ice hockey coach best known for building Michigan Tech into a national powerhouse during his long tenure.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8d3855d50819097fc8561b0299dd9 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e531d722808190a97828cae8e3846e |
completed | April 19, 2026, 7:49 p.m. |
Created at: April 10, 2026, 11:35 a.m.