Triple
T23160603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Epsom to London Bridge route |
E578569
|
entity |
| Predicate | centralLondonTerminus |
P146904
|
FINISHED |
| Object | London Bridge railway station |
—
|
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: London Bridge railway station | Statement: [Epsom to London Bridge route, centralLondonTerminus, London Bridge railway station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: centralLondonTerminus Context triple: [Epsom to London Bridge route, centralLondonTerminus, London Bridge railway station]
-
A.
primaryLondonTerminal
Indicates that a given station serves as the main London terminal for a particular rail service or route.
-
B.
secondaryLondonTerminal
Indicates that a location serves as a secondary terminal in London associated with a primary London terminal for a given service or route.
-
C.
londonTerminusStreet
Indicates that a street serves as a terminus (end point) for transport routes in London.
-
D.
originalLondonTerminusLocation
Indicates the location of an entity’s original terminus station in London.
-
E.
hasTerminusInCentralLondon
chosen
Indicates that the route, service, or line ends at a terminal point located within Central London.
- 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_69e245fc75348190a0288401044c8af8 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f006930819097aafef87405d737 |
completed | April 29, 2026, 4:54 a.m. |
| PD | Predicate disambiguation | batch_69ef89ff76808190808ee4ad9dea776b |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:02 p.m.