Triple
T2088610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Westinghouse air brake system |
E32613
|
entity |
| Predicate | improved |
P6555
|
FINISHED |
| Object | train stopping distance |
—
|
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 stopping distance | Statement: [Westinghouse air brake system, improved, train stopping distance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: improved Context triple: [Westinghouse air brake system, improved, train stopping distance]
-
A.
improvesOn
chosen
Indicates that one entity enhances, refines, or performs better than another entity, typically by addressing its limitations or increasing its effectiveness.
-
B.
updated
Indicates that an entity has been modified or brought to a more recent state compared to its previous version or status.
-
C.
influenced
Indicates that one entity has affected, shaped, or altered another entity’s state, behavior, or characteristics.
-
D.
increases
Indicates that one entity causes another entity’s value, level, or intensity to become larger or higher.
-
E.
achieved
Indicates that an entity successfully reached, obtained, or accomplished a specified goal, result, or state.
- 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_69a885eba0708190999696a45cbec816 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abba712388819091d68a4bb99f6b17 |
completed | March 7, 2026, 5:41 a.m. |
| PD | Predicate disambiguation | batch_69abb7b4356881909217c42ccb8bb1ed |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:43 p.m.