Triple
T3416637
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eielson Air Force Base |
E72024
|
entity |
| Predicate | hostsExerciseType |
P8834
|
FINISHED |
| Object | large-force air combat exercise |
—
|
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: large-force air combat exercise | Statement: [Eielson Air Force Base, hostsExerciseType, large-force air combat exercise]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostsExerciseType Context triple: [Eielson Air Force Base, hostsExerciseType, large-force air combat exercise]
-
A.
participatesInExercise
Indicates that an entity takes part in a physical exercise activity or workout.
-
B.
freeExerciseTest
Indicates a legal assessment of whether a law or government action improperly burdens or restricts an individual’s or group’s free exercise of religion.
-
C.
hasExerciseFeatures
Indicates that something possesses specific characteristics, attributes, or properties related to exercise or physical activity.
-
D.
hasOrdinaryExercise
Indicates that an entity engages in or is associated with a regular, non-specialized form of physical exercise.
-
E.
activityType
chosen
Indicates the specific kind or category of action or event that an entity is engaged in or associated with.
- 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_69ad85ad38e48190b7660c5118a35289 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb92ae6148190958d6bb735258cab |
completed | March 8, 2026, 6 p.m. |
| PD | Predicate disambiguation | batch_69adadfcbc38819080852c18240451c5 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:15 p.m.