Triple
T12820879
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | T-2 Buckeye |
E306524
|
entity |
| Predicate | T-2CEngine |
P2092
|
FINISHED |
| Object | two General Electric J85 turbojets |
—
|
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: two General Electric J85 turbojets | Statement: [T-2 Buckeye, T-2CEngine, two General Electric J85 turbojets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: T-2CEngine Context triple: [T-2 Buckeye, T-2CEngine, two General Electric J85 turbojets]
-
A.
typicalEngine
chosen
Indicates that an entity is the standard or commonly used engine for another entity (such as a vehicle, device, or system).
-
B.
E2Term
Indicates that an entity serves as the second term or argument in a binary relation or expression.
-
C.
thirdStageEngineType
Indicates the specific type or model of engine used in the third stage of a multi-stage launch vehicle or rocket.
-
D.
testedEngineType
Indicates that an engine of a specified type has been subjected to a test or evaluation.
-
E.
TCcode
Indicates a relationship where an entity is associated with, identified by, or classified using a specific TC (technical/transaction/control) code.
- 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.