Triple
T27873687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GE U-series locomotives |
E704867
|
entity |
| Predicate | typicalPrimeMoverFamily |
P191392
|
FINISHED |
| Object | GE FDL |
—
|
NE NERFINISHED |
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: GE FDL | Statement: [GE U-series locomotives, typicalPrimeMoverFamily, GE FDL]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalPrimeMoverFamily Context triple: [GE U-series locomotives, typicalPrimeMoverFamily, GE FDL]
-
A.
primeMoverFamily
Indicates that one entity is the primary driving or originating force behind another within a familial or foundational relationship.
-
B.
powerUnitFamily
chosen
Indicates that one power unit belongs to, or is categorized within, a broader family or series of related power units.
-
C.
typicalPower
Indicates the usual or characteristic amount of power associated with an entity under normal operating conditions.
-
D.
powerUnitType
Indicates the type or category of power unit associated with or used by an entity.
-
E.
typicalTurbineType
Indicates the turbine type that is most commonly or characteristically used or found in association with a given entity or context.
- 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_69ef84111bb4819084298f994b31c62f |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_6a002e71bdc48190b922f2d3b362d259 |
completed | May 10, 2026, 7:06 a.m. |
| PD | Predicate disambiguation | batch_6a002e1a28708190b65f9e657c770bab |
completed | May 10, 2026, 7:04 a.m. |
Created at: April 27, 2026, 6:26 p.m.