Triple
T1291584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A90 road |
E27559
|
entity |
| Predicate | connectsCity |
P4245
|
FINISHED |
| Object | Fraserburgh |
E214447
|
NE 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: Fraserburgh | Statement: [A90 road, connectsCity, Fraserburgh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fraserburgh Context triple: [A90 road, connectsCity, Fraserburgh]
-
A.
Fraserburgh
chosen
Fraserburgh is a coastal town in Aberdeenshire, Scotland, known historically for its busy fishing port and maritime heritage.
-
B.
Musselburgh
Musselburgh is a historic coastal town in East Lothian, Scotland, situated just east of Edinburgh and known for its racecourse and fishing heritage.
-
C.
Aberdour
Aberdour is a coastal village in Fife, Scotland, known for its historic castle, scenic beaches, and role as a commuter stop between Edinburgh and the Fife region.
-
D.
Peterhead
Peterhead is a coastal town in Aberdeenshire, northeast Scotland, known historically for its fishing industry and maritime heritage.
-
E.
Gourock
Gourock is a coastal town and ferry port on the Firth of Clyde in Inverclyde, western Scotland.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69a496d4ec448190ad653b2590c46711 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c0d7d15081909d3af19b9297f1cc |
completed | March 1, 2026, 10:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adfb84cf088190bf40917cfcc98446 |
completed | March 8, 2026, 10:43 p.m. |
Created at: March 1, 2026, 7:51 p.m.