Triple
T35838518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Exhibition Centre station |
E1036008
|
entity |
| Predicate | adjacentStationOnEastRailLine |
P192094
|
FINISHED |
| Object | Admiralty 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: Admiralty station | Statement: [Exhibition Centre station, adjacentStationOnEastRailLine, Admiralty station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adjacentStationOnEastRailLine Context triple: [Exhibition Centre station, adjacentStationOnEastRailLine, Admiralty station]
-
A.
adjacentStationOnCentralLineTowardsEast
Indicates that one station is directly next to another along the Central Line in the eastbound direction.
-
B.
adjacentStationOnEastLondonLine
Indicates that one station is directly next to another station along the East London Line.
-
C.
adjacentStationOnRobinHoodLine
Indicates that one station is directly next to another station along the Robin Hood railway line.
-
D.
adjacentStationOnLine
Indicates that one station is directly next to another station along the same transit line, with no other station in between.
-
E.
adjacentStationOnNorthernLine
Indicates that one station is directly next to another station along the Northern Line, with no other stations in between.
- F. None of above. chosen
Provenance (4 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_69f76e1a29e8819088280f26096aeb55 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fcf36d2894819089b7db8e91b63c9d |
completed | May 7, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69fcf25c0a108190bfa823474098640b |
completed | May 7, 2026, 8:13 p.m. |
| PDg | Predicate description generation | batch_69fcf36bb86c8190a0a0ccf47cb56e5c |
completed | May 7, 2026, 8:17 p.m. |
Created at: May 3, 2026, 4:06 p.m.