Triple
T6708081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Warminster railway station |
E153057
|
entity |
| Predicate | hasTrainClass |
P56947
|
FINISHED |
| Object | diesel multiple units |
—
|
LITERAL FINISHED |
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: diesel multiple units | Statement: [Warminster railway station, hasTrainClass, diesel multiple units]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTrainClass Context triple: [Warminster railway station, hasTrainClass, diesel multiple units]
-
A.
trainTypeUsed
chosen
Indicates that a specific type or category of train is employed or operated in a given context or service.
-
B.
hasCabinClass
Indicates that an entity (such as a booking, ticket, or seat) is associated with a specific cabin class (e.g., economy, business, first).
-
C.
railroadClass
Indicates the classification or category of a railroad according to an established system (e.g., by size, revenue, or regulatory status).
-
D.
hasRailMode
Indicates that an entity is associated with or supports transportation via rail-based modes (such as trains, trams, or subways).
-
E.
carriageType
Indicates the specific kind or category of carriage associated with or used in relation to an entity.
- 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_69c68808d8d8819087369015270788fe |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d16897e48190b43eda2206b14d6a |
completed | March 27, 2026, 6:50 p.m. |
| PD | Predicate disambiguation | batch_69c6d089c7488190a00853fb12f53b2a |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:06 p.m.