Triple
T2732911
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A955 road |
E60356
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Buckhaven |
E8174
|
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: Buckhaven | Statement: [A955 road, connects, Buckhaven]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Buckhaven Context triple: [A955 road, connects, Buckhaven]
-
A.
Buckhaven
chosen
Buckhaven is a coastal town in eastern Scotland, situated on the Firth of Forth in the historic county of Fife.
-
B.
Milnerton
Milnerton is a coastal suburb of Cape Town in South Africa, known for its beaches, lagoon, and views across Table Bay toward Table Mountain.
-
C.
Lankershim
Lankershim is a surname most notably associated with Isaac Lankershim, a 19th-century landowner and developer influential in the early growth of the Los Angeles area.
-
D.
Seaton Carew
Seaton Carew is a coastal village and seaside resort in County Durham, England, known for its sandy beach and promenade along the North Sea.
-
E.
Amberlea
Amberlea is a residential neighbourhood located in the city of Pickering in the Greater Toronto Area of Ontario, Canada.
- 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_69ab4b75cd908190b691ef0d1801acda |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdaf175808190acbbb3873c7c3f67 |
completed | March 7, 2026, 7:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afbbc430ec8190a54f805cd0067b97 |
completed | March 10, 2026, 6:35 a.m. |
Created at: March 6, 2026, 9:56 p.m.