Triple
T9302168
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hatfield rail crash |
E223790
|
entity |
| Predicate | speedAtDerailmentApprox |
P87957
|
FINISHED |
| Object | 115 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: 115 mph | Statement: [Hatfield rail crash, speedAtDerailmentApprox, 115 mph]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: speedAtDerailmentApprox Context triple: [Hatfield rail crash, speedAtDerailmentApprox, 115 mph]
-
A.
relativeSpeedComparedToConventionalTrains
Indicates how the speed of something compares to that of conventional trains, typically expressing whether it is faster, slower, or similar.
-
B.
usesRailGauge
Indicates that one entity (typically a railway system or line) operates using the specified rail gauge measurement of the other entity.
-
C.
railcode
Indicates that an entity is associated with a specific railway code used for identification or classification within a rail system.
-
D.
maxSpeed
Indicates the greatest possible speed at which an entity can move or operate under specified conditions.
-
E.
speedLimitCharacteristic
Indicates that an entity has a specific speed limit property or constraint associated with it.
- F. None of above. chosen
Provenance (4 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_69ca8424d0f08190831e2e93c6533aeb |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd08d34c4c819095a213360747c3a6 |
completed | April 1, 2026, noon |
| PD | Predicate disambiguation | batch_69cc7a5ef1908190bc5ca166bb895af6 |
completed | April 1, 2026, 1:52 a.m. |
| PDg | Predicate description generation | batch_69cc955a38108190b602d1e73725f11b |
completed | April 1, 2026, 3:47 a.m. |
Created at: March 30, 2026, 7:36 p.m.