Triple
T12820877
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | T-2 Buckeye |
E306524
|
entity |
| Predicate | T-2AEngine |
P38991
|
FINISHED |
| Object | single Westinghouse J34 turbojet |
—
|
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 Westinghouse J34 turbojet | Statement: [T-2 Buckeye, T-2AEngine, single Westinghouse J34 turbojet]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: T-2AEngine Context triple: [T-2 Buckeye, T-2AEngine, single Westinghouse J34 turbojet]
-
A.
tugAircraft
Indicates that one entity tows or pulls an aircraft, typically using a tug vehicle or similar equipment.
-
B.
aircraftEngineType
chosen
Indicates the specific type or classification of engine that an aircraft uses.
-
C.
aircraftPowerplantType
Indicates the type or category of powerplant (e.g., engine or propulsion system) used by an aircraft.
-
D.
wingMountedEngines
Indicates that the engines of an aircraft are mounted on its wings rather than on other parts of the airframe.
-
E.
Tu-128UTRole
Indicates that the relationship involves the Tu-128UT variant specifically in its designated operational role or function.
- 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_69d7bdf46c448190b1faa55aaacb6317 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e9e5a2481908921d097df541db8 |
completed | April 10, 2026, 9:41 p.m. |
| PD | Predicate disambiguation | batch_69d964100f7481909a197396003d4a71 |
completed | April 10, 2026, 8:56 p.m. |
Created at: April 9, 2026, 5:31 p.m.