Triple
T26078407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roughton Road railway station |
E657758
|
entity |
| Predicate | distanceFromNorwichByRail |
P4778
|
FINISHED |
| Object | 28 miles 22 chains |
—
|
LITERAL 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: 28 miles 22 chains | Statement: [Roughton Road railway station, distanceFromNorwichByRail, 28 miles 22 chains]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceFromNorwichByRail Context triple: [Roughton Road railway station, distanceFromNorwichByRail, 28 miles 22 chains]
-
A.
distanceFromNorwich
chosen
Indicates the measured distance between a given place or object and the location of Norwich.
-
B.
nextStationOnLineTowardsNorwich
Indicates that one station is the immediately following station along a railway line in the direction of Norwich.
-
C.
directionFromNorwich
Indicates the relative compass direction or bearing of one place or object as measured outward starting from Norwich.
-
D.
distanceFromBanburyByRail
Indicates the distance between a place and Banbury when traveling by railway.
-
E.
distanceToBideford_km
Indicates the physical distance, measured in kilometers, between a given place or object and Bideford.
- F. None of above.
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_69ee5bbf0d208190801ee95d4f07fb16 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69fd5f29b1988190877764ef2a399c7f |
completed | May 8, 2026, 3:57 a.m. |
| PD | Predicate disambiguation | batch_69fd5e30194c819085b5ce586122ab37 |
completed | May 8, 2026, 3:53 a.m. |
Created at: April 26, 2026, 7:36 p.m.