Triple
T4643396
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue Impulse |
E101706
|
entity |
| Predicate | formationFlying |
P57566
|
FINISHED |
| Object | precision close-formation aerobatics |
—
|
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: precision close-formation aerobatics | Statement: [Blue Impulse, formationFlying, precision close-formation aerobatics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formationFlying Context triple: [Blue Impulse, formationFlying, precision close-formation aerobatics]
-
A.
onFormation
Indicates that one entity is located on or attached to the surface of a formation (such as a geological or structural feature).
-
B.
tacticalFormation
Indicates a specific strategic arrangement or positioning of entities relative to one another to achieve a tactical objective.
-
C.
bandFormation
Indicates the event or process by which a musical band is created or comes together as a group.
-
D.
notableAirFormation
Indicates a significant or noteworthy configuration, pattern, or structure formed in the air (such as clouds, smoke, or other aerial phenomena).
-
E.
formsSwarms
Indicates that multiple entities come together to create or participate in a coordinated swarm.
- 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_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. |
| PDg | Predicate description generation | batch_69bd56b5f4648190834eafa666d53caa |
completed | March 20, 2026, 2:16 p.m. |
Created at: March 20, 2026, 1:14 p.m.