Triple
T38161094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Minories railway station |
E953019
|
entity |
| Predicate | nearbySuccessorStation |
P46397
|
FINISHED |
| Object | Fenchurch Street 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: Fenchurch Street railway station | Statement: [Minories railway station, nearbySuccessorStation, Fenchurch Street railway station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nearbySuccessorStation Context triple: [Minories railway station, nearbySuccessorStation, Fenchurch Street railway station]
-
A.
successorStation
chosen
Indicates that one station directly follows another in a sequence, such as along a transit line or route.
-
B.
adjacentStationTowards
Indicates that one station is directly next to another station in a specified direction along a route or line.
-
C.
adjacentStationOnA
Indicates that one station is directly next to another station along line A in the network.
-
D.
successorLocation
Indicates that one location directly follows or comes after another in a defined spatial or ordered sequence.
-
E.
adjacentStationOnLineS1
Indicates that one station is directly next to another station along railway line S1, with no other stations in between.
- 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_69f76f0b93c48190a117319ab3a9f282 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69ff38b960808190a8263348f1e5c0e4 |
completed | May 9, 2026, 1:38 p.m. |
| PD | Predicate disambiguation | batch_69ff37d97d9c8190849b2bac14f9af1d |
completed | May 9, 2026, 1:34 p.m. |
Created at: May 3, 2026, 4:21 p.m.