Triple
T21772206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | XF-108 Rapier |
E537460
|
entity |
| Predicate | intendedAvionics |
P7133
|
FINISHED |
| Object | long-range search radar |
—
|
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: long-range search radar | Statement: [XF-108 Rapier, intendedAvionics, long-range search radar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intendedAvionics Context triple: [XF-108 Rapier, intendedAvionics, long-range search radar]
-
A.
intendedAircraft
Indicates that an aircraft is the one planned or designated to be used for a particular flight, mission, or operation.
-
B.
avionics
chosen
Indicates that an entity is related to the electronic systems used to control, monitor, or assist the operation of aircraft or spacecraft.
-
C.
avionicsSupplier
Indicates that one entity supplies avionics systems, components, or related services to another entity.
-
D.
isPartOfAviationSystem
Indicates that something functions as a component or subsystem within a broader aviation system or infrastructure.
-
E.
avionicsOrigin
Indicates the source or originating location from which the avionics system or components are derived, produced, or supplied.
- 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_69e0c470759c819094a215757113562b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f031af6a488190a2dcebed43d199d4 |
completed | April 28, 2026, 4:03 a.m. |
| PD | Predicate disambiguation | batch_69e6be6299988190a34c98fa76d94700 |
completed | April 21, 2026, 12:01 a.m. |
Created at: April 16, 2026, 6:51 p.m.