Triple
T625753
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wright J-5C Whirlwind |
E15813
|
entity |
| Predicate | powerplantFor |
P17850
|
FINISHED |
| Object | single-engine monoplanes |
—
|
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: single-engine monoplanes | Statement: [Wright J-5C Whirlwind, powerplantFor, single-engine monoplanes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: powerplantFor Context triple: [Wright J-5C Whirlwind, powerplantFor, single-engine monoplanes]
-
A.
powerplant
Indicates that an entity functions as a facility or installation where energy sources are converted into usable power, typically electricity.
-
B.
powerplantRole
Indicates that one entity serves in a specific functional or operational role relative to a power plant.
-
C.
energyType
Indicates the kind or category of energy associated with an entity or process.
-
D.
suppliesPowerTo
Indicates that one entity provides electrical or energy power required for the operation or functioning of another entity.
-
E.
numberOfPowerhouses
Indicates the quantity of powerhouse entities associated with or contained by a given subject.
- 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_69a4935c131c8190a5378c6bf101e8cc |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49e574444819087999404f3e3ffd9 |
completed | March 1, 2026, 8:15 p.m. |
| PD | Predicate disambiguation | batch_69a49d0069d0819087c83b608f6fc053 |
completed | March 1, 2026, 8:09 p.m. |
| PDg | Predicate description generation | batch_69a49e2107548190af0c1d67cfa475d1 |
completed | March 1, 2026, 8:14 p.m. |
Created at: March 1, 2026, 7:35 p.m.