Triple
T28094121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GE ES44C4 |
E710037
|
entity |
| Predicate | horsepowerClass |
P5894
|
FINISHED |
| Object | high-horsepower freight locomotive |
—
|
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: high-horsepower freight locomotive | Statement: [GE ES44C4, horsepowerClass, high-horsepower freight locomotive]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: horsepowerClass Context triple: [GE ES44C4, horsepowerClass, high-horsepower freight locomotive]
-
A.
horsepower
chosen
Indicates the power output or performance capacity associated with an entity, typically measuring how much work it can perform over time.
-
B.
powerClassBR
Indicates a relationship where one entity is classified or grouped according to its power-related category or level relative to another entity.
-
C.
hasEngineDisplacementClass
Indicates a relationship where a vehicle or engine is assigned to a category based on the size or volume of its engine displacement.
-
D.
vehiclePower
Indicates the amount or type of power a vehicle can produce or is rated to deliver.
-
E.
powerToWeightRatio
Indicates the relationship between an entity’s available power and its mass, expressing how much power is provided per unit of weight.
- 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_69ef9b70fd108190a875953b2e50ca91 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f6406d517481908e5b24b2f41c585b |
completed | May 2, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 9 p.m.