Triple
T21624678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Kamdesh |
E533667
|
entity |
| Predicate | airSupportUsed |
P6269
|
FINISHED |
| Object | U.S. Air Force close air support |
—
|
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: U.S. Air Force close air support | Statement: [Battle of Kamdesh, airSupportUsed, U.S. Air Force close air support]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airSupportUsed Context triple: [Battle of Kamdesh, airSupportUsed, U.S. Air Force close air support]
-
A.
airSupport
chosen
Indicates that one entity provides aerial assistance or backing to another, typically through aircraft-based protection, transport, or attack.
-
B.
airSupportPlannedFrom
Indicates that air support operations are scheduled or intended to be provided starting from a specified source or location.
-
C.
hasPassengerAirlineService
Indicates that a location or facility is served by scheduled passenger airline flights.
-
D.
airLegType
Indicates the specific type or category of an air travel segment within an itinerary (e.g., flight leg classification or role).
-
E.
airlinesUse
Indicates that certain airlines operate, employ, or make use of a specified resource, service, or system.
- 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_69e0c464fba881908d0ff2ac80511ce1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef52121c3c8190b9b4d862ed247c71 |
completed | April 27, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69e69665fe8c8190af7e38785db188b2 |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:34 p.m.