Triple
T8556161
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jakt, Attack och Spaning 39 |
E202567
|
entity |
| Predicate | denotesGeneration |
P83606
|
FINISHED |
| Object | 39-series Swedish combat aircraft |
—
|
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: 39-series Swedish combat aircraft | Statement: [Jakt, Attack och Spaning 39, denotesGeneration, 39-series Swedish combat aircraft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: denotesGeneration Context triple: [Jakt, Attack och Spaning 39, denotesGeneration, 39-series Swedish combat aircraft]
-
A.
targetGenerationDepicted
Indicates that one entity visually represents or portrays the generation (age cohort) associated with another entity.
-
B.
generationOf
Indicates that one entity is the origin, creator, or producer of another entity.
-
C.
finalGenerationOf
Indicates that one entity represents the last or ultimate generation or iteration in a sequence or lineage of another entity.
-
D.
dominantGeneration
Indicates that one generation in a life cycle is more prominent, long-lived, or visually conspicuous than the other generation(s).
-
E.
currentGeneration
Indicates that an entity belongs to or is associated with the presently living or active generation within a temporal or lineage sequence.
- F. None of above. chosen
Provenance (4 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_69ca832610e08190b3b6c6cd2c250255 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe88bcce081909e12e4037a0e6323 |
completed | March 31, 2026, 3:30 p.m. |
| PD | Predicate disambiguation | batch_69cbd1160fcc8190aa380a73610af731 |
completed | March 31, 2026, 1:50 p.m. |
| PDg | Predicate description generation | batch_69cbe30e37ac8190b685df36274602b5 |
completed | March 31, 2026, 3:06 p.m. |
Created at: March 30, 2026, 6:19 p.m.