Triple
T19187389
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Golborne South railway station |
E469739
|
entity |
| Predicate | hadStationBuilding |
P1711
|
FINISHED |
| Object | brick-built station building |
—
|
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: brick-built station building | Statement: [Golborne South railway station, hadStationBuilding, brick-built station building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadStationBuilding Context triple: [Golborne South railway station, hadStationBuilding, brick-built station building]
-
A.
hasStationBuilding
chosen
Indicates that a station is associated with or includes a station building as part of its facilities.
-
B.
hasStationHall
Indicates that one entity (typically a station) includes or is associated with a station hall area as part of its structure or facilities.
-
C.
hadStationHotel
Indicates that a railway station possessed or was associated with a hotel facility serving its passengers or operations.
-
D.
hadRailwayStation
Indicates that a place or area previously possessed a railway station, which may no longer be in existence or operation.
-
E.
hasStationAt
Indicates that an entity maintains or operates a station located at a specified place.
- 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_69d8dd0ad9088190a173b32657ae2e7a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f89f3ebc8190ba01ae075ffc77df |
completed | April 20, 2026, 9:57 a.m. |
| PD | Predicate disambiguation | batch_69e4b9bb158481909478ca2e06f3ba39 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:07 p.m.