Triple
T3724080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saab 37 Viggen |
E81705
|
entity |
| Predicate | SK 37 ViggenRole |
P50367
|
FINISHED |
| Object | two-seat trainer |
—
|
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: two-seat trainer | Statement: [Saab 37 Viggen, SK 37 ViggenRole, two-seat trainer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: SK 37 ViggenRole Context triple: [Saab 37 Viggen, SK 37 ViggenRole, two-seat trainer]
-
A.
testAircraftRole
chosen
Indicates that an aircraft is assigned or evaluated for a specific operational role or function.
-
B.
aircraftConfigurationProduced
Indicates that a specific aircraft configuration has been manufactured or produced.
-
C.
basedAircraftRole
Indicates that an aircraft is regularly stationed at a particular location in a specified operational role or function.
-
D.
mainFighterAircraft
Indicates that an aircraft serves as the primary fighter aircraft for a given country, organization, or military force.
-
E.
fighter1
Indicates that the subject is the first participant or primary combatant in a fight or competitive physical confrontation.
- 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_69ad8b1b7ef081908d2d381bbf54985a |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcaf3f2ec8190a3a8f363cfb762f3 |
completed | March 8, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_69adc0452f5081909c79e114a86cce8c |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:34 p.m.