Triple
T20748502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manchester to Chester line |
E510651
|
entity |
| Predicate | via |
P5680
|
FINISHED |
| Object | Cuddington |
—
|
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: Cuddington | Statement: [Manchester to Chester line, via, Cuddington]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cuddington Context triple: [Manchester to Chester line, via, Cuddington]
-
A.
Cuddington
chosen
Cuddington is a village in Cheshire, England, served by a station on the Manchester–Chester railway line.
-
B.
Cuddington
Cuddington is a small village and civil parish in Buckinghamshire, England, known for its historic buildings and rural character.
-
C.
Kerrington
Kerrington is a given name and surname, likely a modern or alternative spelling variant of Carrington.
-
D.
Gravenhurst
Gravenhurst is a small town in Ontario, Canada, known as a gateway to the Muskoka cottage country and its scenic lakeside tourism.
-
E.
Jamisontown
Jamisontown is a residential suburb in western Sydney, New South Wales, Australia, situated near the regional centre of Penrith.
- 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_69e0b4c845e88190b4c5f3ae79291182 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c228af288190a20829d45c034c24 |
completed | April 21, 2026, 12:17 a.m. |
Created at: April 16, 2026, 12:34 p.m.