Triple
T2515387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 446th Airlift Wing |
E55399
|
entity |
| Predicate | aircraftMission |
P22637
|
FINISHED |
| Object | intertheater airlift |
—
|
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: intertheater airlift | Statement: [446th Airlift Wing, aircraftMission, intertheater airlift]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aircraftMission Context triple: [446th Airlift Wing, aircraftMission, intertheater airlift]
-
A.
pilotLaterMission
Indicates that an entity serves as the pilot of a mission that occurs after a referenced or earlier mission.
-
B.
typeOfMission
chosen
Indicates the specific category or nature of a mission that an entity is associated with or engaged in.
-
C.
targetedAircraft
Indicates that one entity has selected or designated an aircraft as the object of an attack, tracking, or other directed action.
-
D.
missionPlanning
Indicates the process of defining, organizing, and coordinating actions or operations needed to achieve a specific mission objective.
-
E.
airForceUserPlanned
Indicates that an air force user has scheduled or intends to carry out a specific action or operation.
- 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_69ab49e4749c8190813311efd1630f1b |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd5a33234819082ad49fa6594b6be |
completed | March 7, 2026, 7:37 a.m. |
| PD | Predicate disambiguation | batch_69abd0bf37c0819088d28b5081ba7556 |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:46 p.m.