Triple
T30440401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soham rail disaster |
E774423
|
entity |
| Predicate | railwayStationAffected |
P154579
|
FINISHED |
| Object | Soham 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: Soham railway station | Statement: [Soham rail disaster, railwayStationAffected, Soham railway station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: railwayStationAffected Context triple: [Soham rail disaster, railwayStationAffected, Soham railway station]
-
A.
trainStationAffected
chosen
Indicates that a train station is impacted or influenced by a particular event, condition, or action.
-
B.
railwayStationOnLine
Indicates that a particular railway station is located on and served by a specified railway line.
-
C.
otherRailwayStation
Indicates a relationship where one railway station is associated with another as a distinct but related station, such as an alternative, nearby, or counterpart station.
-
D.
railTerminus
Indicates that a railway line or service ends at a particular station or location, which serves as its final terminus.
-
E.
railwayTraffic
Indicates the presence, flow, or management of train movements along railway lines between locations.
- 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_69f22493ef9c8190ae8c2afcb7f994c8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f7221dc9a88190bb8194fcc29c42bc |
completed | May 3, 2026, 10:23 a.m. |
| PD | Predicate disambiguation | batch_69f72153a9188190b02adc84e1be4af8 |
completed | May 3, 2026, 10:20 a.m. |
Created at: April 29, 2026, 8:08 p.m.