Triple
T10831043
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winchester railway station |
E255617
|
entity |
| Predicate | hasStationBuildingLocation |
P42882
|
FINISHED |
| Object | on the down (southbound) side of the line |
—
|
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: on the down (southbound) side of the line | Statement: [Winchester railway station, hasStationBuildingLocation, on the down (southbound) side of the line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStationBuildingLocation Context triple: [Winchester railway station, hasStationBuildingLocation, on the down (southbound) side of the line]
-
A.
hasStationBuilding
Indicates that a station is associated with or includes a station building as part of its facilities.
-
B.
hasStationHouseLocation
Indicates that a station house is located at or associated with a specific place or geographic location.
-
C.
hasBuildingLocation
chosen
Indicates that a building is situated at, or associated with, a specific geographic or spatial location.
-
D.
hasStationHall
Indicates that one entity (typically a station) includes or is associated with a station hall area as part of its structure or facilities.
-
E.
hasStationInCity
Indicates that a station or facility is located within a particular city.
- 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_69d6aa8081448190a9324184f2bd1c26 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d744222288819093258b452569acab |
completed | April 9, 2026, 6:16 a.m. |
| PD | Predicate disambiguation | batch_69d70d25280c8190b648d7d1958b413a |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:19 p.m.