Triple
T33095333
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flagon |
E846892
|
entity |
| Predicate | subjectAircraftUser |
P110430
|
FINISHED |
| Object | Soviet Air Defence Forces |
—
|
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: Soviet Air Defence Forces | Statement: [Flagon, subjectAircraftUser, Soviet Air Defence Forces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subjectAircraftUser Context triple: [Flagon, subjectAircraftUser, Soviet Air Defence Forces]
-
A.
aircraftUsers
chosen
Indicates that one entity uses, operates, or employs an aircraft associated with another entity.
-
B.
referredAircraftPrimaryUser
Indicates that one entity is identified as the main or primary user/operator of the referenced aircraft.
-
C.
sharesAircraftWith
Indicates that two or more entities use, operate, or are associated with the same aircraft.
-
D.
associatedWithAircraftModel
Indicates that something has a specified relationship or connection to a particular aircraft model.
-
E.
operatorOfReferencedAircraft
Indicates that one entity serves as the operator (e.g., managing or controlling party) of an aircraft that is referenced elsewhere in the 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_69f3495590dc8190aa04f3dec74ce976 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69fd231cab588190ad0953dc8f4af8f2 |
completed | May 7, 2026, 11:41 p.m. |
| PD | Predicate disambiguation | batch_69fd1aa3f1c481909fe6e9cab1383551 |
completed | May 7, 2026, 11:05 p.m. |
Created at: May 1, 2026, 1:26 a.m.