Triple
T28826302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Parkside West Junction |
E727914
|
entity |
| Predicate | formerAssociatedStation |
P65217
|
FINISHED |
| Object | Parkside 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: Parkside station | Statement: [Parkside West Junction, formerAssociatedStation, Parkside station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerAssociatedStation Context triple: [Parkside West Junction, formerAssociatedStation, Parkside station]
-
A.
associatedStation
Indicates a relationship where one entity is linked or connected to a particular station as its relevant or related station.
-
B.
adjacentStationFormerly
Indicates that two stations were directly adjacent to each other in the past, but are no longer adjacent in the current network configuration.
-
C.
hasFormerStation
chosen
Indicates that an entity previously had a particular station (e.g., a stop, depot, or facility) that is no longer in active use or part of its current infrastructure.
-
D.
formerStationNameFor
Indicates that one station name was previously used as the official name for another station.
-
E.
formerRadioStation
Indicates that the subject was once a radio station but no longer operates in that capacity.
- 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_69f0319dc6088190bbfaa206d40ed74a |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69fe12a899d4819080d48423f32eace9 |
completed | May 8, 2026, 4:43 p.m. |
| PD | Predicate disambiguation | batch_69fe0d7f6aa08190a1d2dfc025d4e0dc |
completed | May 8, 2026, 4:21 p.m. |
Created at: April 28, 2026, 6:36 a.m.