Triple
T23196071
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | British Rail second-generation DMUs |
E579870
|
entity |
| Predicate | typical maximum speed |
P2096
|
FINISHED |
| Object | 75–125 mph |
—
|
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: 75–125 mph | Statement: [British Rail second-generation DMUs, typical maximum speed, 75–125 mph]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typical maximum speed Context triple: [British Rail second-generation DMUs, typical maximum speed, 75–125 mph]
-
A.
maxSpeed
chosen
Indicates the greatest possible speed at which an entity can move or operate under specified conditions.
-
B.
designedSpeedKmH
Indicates the maximum speed in kilometers per hour that something is intended or engineered to achieve under its design specifications.
-
C.
hasTopSpeedSection
Indicates that an entity includes or is associated with a segment or portion where the maximum or top speed is defined, reached, or relevant.
-
D.
hasTypicalVelocity
Indicates that an entity is associated with a characteristic or commonly observed speed at which it typically moves or operates.
-
E.
designedServiceSpeed
Indicates the intended or specified operational speed at which a service is designed to function.
- 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_69e24600eed08190bd7e5295653a1503 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18fdb279c81908dcc46f2786a86cd |
completed | April 29, 2026, 4:58 a.m. |
| PD | Predicate disambiguation | batch_69ef8a041c0081909afb670d17a5aaba |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:06 p.m.