Triple
T31034837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southall rail crash |
E790825
|
entity |
| Predicate | passengerTrainOrigin |
P170434
|
FINISHED |
| Object | Swansea |
—
|
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: Swansea | Statement: [Southall rail crash, passengerTrainOrigin, Swansea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: passengerTrainOrigin Context triple: [Southall rail crash, passengerTrainOrigin, Swansea]
-
A.
majorTrainOrigin
Indicates that a location serves as a primary starting point or origin for major train services or routes.
-
B.
hasRailwayCompanyOrigin
Indicates that a railway company originated from, or was initially established in, a specified place or source.
-
C.
railLineOrigin
Indicates that a rail line begins or originates from a specified location or point.
-
D.
hasRollingStockOrigin
Indicates that a piece of rolling stock originates from, or was initially based in, a particular location or source.
-
E.
railDisasterTrainOrigin
chosen
Indicates the place from which a train involved in a rail disaster originally departed.
- 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_69f224c97a788190b5da1ead6038a74e |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f7117e55908190a67105e92bc4830f |
completed | May 3, 2026, 9:12 a.m. |
| PD | Predicate disambiguation | batch_69f70f380690819090cc34763ba460ed |
completed | May 3, 2026, 9:02 a.m. |
Created at: April 29, 2026, 8:59 p.m.