Triple
T25867033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gulfstream G550 |
E651644
|
entity |
| Predicate | avionicsBasedOn |
P7133
|
FINISHED |
| Object | Honeywell Primus Epic |
—
|
NE NERFINISHED |
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: Honeywell Primus Epic | Statement: [Gulfstream G550, avionicsBasedOn, Honeywell Primus Epic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: avionicsBasedOn Context triple: [Gulfstream G550, avionicsBasedOn, Honeywell Primus Epic]
-
A.
basedOnAircraft
Indicates that one entity is derived from, modeled after, or otherwise uses a particular aircraft as its basis or primary reference.
-
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.
avionicsOrigin
Indicates the source or originating location from which the avionics system or components are derived, produced, or supplied.
-
E.
isPartOfAviationSystem
Indicates that something functions as a component or subsystem within a broader aviation system or infrastructure.
- 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_69e7ab3a199c81909227cb964cacfe24 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f602d8f9888190ba2cacc723cc9633 |
completed | May 2, 2026, 1:57 p.m. |
| PD | Predicate disambiguation | batch_69f4939148dc81908706cec7d85291bc |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 22, 2026, 8:07 a.m.