Triple
T18932493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dunnichen |
E463149
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Letham, Angus |
—
|
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: Letham, Angus | Statement: [Dunnichen, near, Letham, Angus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Letham, Angus Context triple: [Dunnichen, near, Letham, Angus]
-
A.
Letham
chosen
Letham is a small village in the Angus council area of eastern Scotland, known for its rural character and local community amenities.
-
B.
Tillicoultry
Tillicoultry is a small town in central Scotland, situated at the foot of the Ochil Hills and historically known for its textile and woollen industries.
-
C.
Dirleton
Dirleton is a historic coastal village in southeastern Scotland, noted for its medieval castle and picturesque setting in East Lothian.
-
D.
Kincardine
Kincardine is a small Scottish town on the north shore of the Firth of Forth, known for its historic bridge and industrial heritage.
-
E.
Kincardine
Kincardine is a lakeside town in Ontario, Canada, known for its scenic Lake Huron shoreline, historic lighthouse, and strong Scottish heritage.
- 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_69d8dcfec90481909e926be9767e5779 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d3e498308190bd1594cca841199c |
completed | April 20, 2026, 7:21 a.m. |
Created at: April 10, 2026, 11:59 a.m.