Triple
T4643439
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hawk T-series |
E101707
|
entity |
| Predicate | roleInAerobatics |
P41047
|
FINISHED |
| Object | aerobatic display aircraft |
—
|
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: aerobatic display aircraft | Statement: [Hawk T-series, roleInAerobatics, aerobatic display aircraft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInAerobatics Context triple: [Hawk T-series, roleInAerobatics, aerobatic display aircraft]
-
A.
hasFixedWingTrainingRole
Indicates that an entity serves in a training capacity specifically related to the operation or use of fixed-wing aircraft.
-
B.
testAircraftRole
Indicates that an aircraft is assigned or evaluated for a specific operational role or function.
-
C.
hasAerobaticDisplayTeam
Indicates that an entity maintains or is associated with a team that performs aerobatic flying displays.
-
D.
flyingDeviceDescribedAs
chosen
Indicates that a flying device is characterized or described in a particular way by some attribute, label, or description.
-
E.
isAviationElementFor
Indicates that something serves as an aviation-related component, feature, or element specifically associated with or used for a particular object, system, 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_69bd43d3bc7c81908f81fcf380476b0f |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5a94486c819087ef8811dcde83b1 |
completed | March 20, 2026, 2:32 p.m. |
| PD | Predicate disambiguation | batch_69bd5234d24c819095c79890b70eff9a |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:14 p.m.