Triple
T35907602
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | J 32E Lansen |
E1038513
|
entity |
| Predicate | hasAirframeOrigin |
P17752
|
FINISHED |
| Object | attack variant of Saab 32 Lansen |
—
|
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: attack variant of Saab 32 Lansen | Statement: [J 32E Lansen, hasAirframeOrigin, attack variant of Saab 32 Lansen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAirframeOrigin Context triple: [J 32E Lansen, hasAirframeOrigin, attack variant of Saab 32 Lansen]
-
A.
airframeDerivedFrom
chosen
Indicates that one airframe design is derived or developed from another pre-existing airframe design.
-
B.
hasRunwayOrigin
Indicates that something originates from, starts at, or is derived from a particular runway.
-
C.
hasAirComponent
Indicates that something includes, contains, or is associated with an air-related component or element.
-
D.
airframeNumber
Indicates the unique identifying number assigned to a specific aircraft’s structural frame within a fleet or system.
-
E.
originOfFlight
Indicates that one location serves as the starting point or departure place for a particular flight.
- 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_69f76e2259608190bf6788a132e0d139 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aa6fd79c8190b1a70068ace78068 |
completed | May 3, 2026, 8:05 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d435288190b30b1991fb003121 |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:07 p.m.