Triple
T16696975
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SPT Subway network |
E405740
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object | Kelvinhall |
E1051278
|
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: Kelvinhall | Statement: [SPT Subway network, hasStation, Kelvinhall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kelvinhall Context triple: [SPT Subway network, hasStation, Kelvinhall]
-
A.
Kelvinhall
chosen
Kelvinhall is a subway station in Glasgow, Scotland, serving the West End near the Kelvingrove Art Gallery and Museum and the University of Glasgow.
-
B.
Larkhall
Larkhall is a small town in central Scotland known historically for its mining and industrial heritage.
-
C.
Larkhall
Larkhall is a district and electoral ward in the London Borough of Lambeth, known for its residential streets, local parks, and proximity to central London.
-
D.
Fountainhall
Fountainhall is a small rural settlement in the Scottish Borders region of Scotland, situated near the Gala Water.
-
E.
Bowhill
Bowhill is an English-language surname of British origin borne by various notable individuals, including military and public figures.
- 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_69d8838db21081909589220fd71440a4 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3832e93c48190a594c498e9cc901a |
completed | April 18, 2026, 1:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00919d02088190acecb1a62a100255 |
completed | May 10, 2026, 2:09 p.m. |
Created at: April 10, 2026, 5:19 a.m.