Triple
T37648884
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cessna T-37 Tweet |
E937113
|
entity |
| Predicate | combatVariant |
P28675
|
FINISHED |
| Object | Cessna A-37 Dragonfly |
—
|
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: Cessna A-37 Dragonfly | Statement: [Cessna T-37 Tweet, combatVariant, Cessna A-37 Dragonfly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: combatVariant Context triple: [Cessna T-37 Tweet, combatVariant, Cessna A-37 Dragonfly]
-
A.
combatArm
Indicates that one entity serves as a primary fighting or operational warfare branch or component of another entity (such as an organization or military force).
-
B.
combatApplication
Indicates the application or use of something (such as skills, tactics, or equipment) within a combat or fighting context.
-
C.
civilianVariant
Indicates that one entity is a civilian version or non-military counterpart of another entity.
-
D.
armedVariants
chosen
Indicates that one entity is a version or model of another that is equipped with weapons or enhanced armaments.
-
E.
missionVariant
Indicates a specific version or configuration of a mission that differs from the standard or base mission.
- 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_69f76ed4fe908190b8061c5c135e0971 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbc36ce1f88190a7fa1656b714e107 |
completed | May 6, 2026, 10:40 p.m. |
| PD | Predicate disambiguation | batch_69fbbd166a488190b1bf9316b0790801 |
completed | May 6, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:18 p.m.