Triple
T24042667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 446 series EMU |
E595426
|
entity |
| Predicate | hasBrakingRole |
P154639
|
FINISHED |
| Object | train braking system |
—
|
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: train braking system | Statement: [446 series EMU, hasBrakingRole, train braking system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBrakingRole Context triple: [446 series EMU, hasBrakingRole, train braking system]
-
A.
hasBraking
Indicates that an entity possesses or is equipped with a braking capability or braking system.
-
B.
hasBrakingZoneFrom
Indicates that an entity has a designated braking zone that originates from or is defined relative to another entity or location.
-
C.
brakeFeature
Indicates that an entity possesses or is equipped with a particular braking-related feature or capability.
-
D.
brakingTestsPerformed
Indicates that one entity has carried out braking tests on another entity or system.
-
E.
brakeType
Indicates the specific kind or system of brakes associated with an entity.
- 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_69e288c06a908190899cad4531f32c9a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d8db3b4c81908a36eace8ec136cc |
completed | April 29, 2026, 10:09 a.m. |
| PD | Predicate disambiguation | batch_69f1764345388190a3102b62ddb729b4 |
completed | April 29, 2026, 3:08 a.m. |
| PDg | Predicate description generation | batch_69f1785afe3c81909be28986ffe944bf |
completed | April 29, 2026, 3:17 a.m. |
Created at: April 17, 2026, 9:58 p.m.