Triple
T7252790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mosquito NF Mk II |
E157644
|
entity |
| Predicate | airborneRadar |
P32605
|
FINISHED |
| Object | AI Mk IV 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: AI Mk IV radar | Statement: [Mosquito NF Mk II, airborneRadar, AI Mk IV radar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airborneRadar Context triple: [Mosquito NF Mk II, airborneRadar, AI Mk IV radar]
-
A.
radarEquipment
chosen
Indicates that one entity is radar equipment used for detecting, tracking, or measuring objects relative to another entity.
-
B.
airbornePlatformFor
Indicates that one entity serves as an airborne platform or carrier used to support, transport, or deploy another entity.
-
C.
airborneComponent
Indicates that one entity is a component or part of another entity specifically when that other entity is in an airborne state.
-
D.
radarType
Indicates the specific category or classification of radar associated with an entity.
-
E.
primaryRadar
Indicates that the relationship or action is detected or established using primary radar sensing (i.e., direct reflection of radio waves from a target without requiring a transponder).
- 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_69c6882d81d4819085f7ff862951ee4f |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea9d41908190bb76c6a5b9d5b1a2 |
completed | March 27, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69c6e7666ffc81908bf643d8257e6337 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:56 p.m.