Triple
T812280
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martinsburg, West Virginia |
E17570
|
entity |
| Predicate | hasMilitaryFacilityNearby |
P15652
|
FINISHED |
| Object |
167th Airlift Wing of the West Virginia Air National Guard
The 167th Airlift Wing of the West Virginia Air National Guard is a military airlift unit that operates transport aircraft and supports global air mobility and homeland defense missions.
|
E97900
|
NE FINISHED |
How this triple was built (5 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: 167th Airlift Wing of the West Virginia Air National Guard | Statement: [Martinsburg, West Virginia, hasMilitaryFacilityNearby, 167th Airlift Wing of the West Virginia Air National Guard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 167th Airlift Wing of the West Virginia Air National Guard Context triple: [Martinsburg, West Virginia, hasMilitaryFacilityNearby, 167th Airlift Wing of the West Virginia Air National Guard]
-
A.
62nd Airlift Wing
The 62nd Airlift Wing is a United States Air Force unit that provides global strategic airlift capabilities, primarily operating C-17 Globemaster III aircraft from Joint Base Lewis–McChord in Washington.
-
B.
89th Airlift Wing
The 89th Airlift Wing is a U.S. Air Force unit based at Joint Base Andrews that provides executive airlift support for the President, Vice President, and other senior government officials.
-
C.
446th Airlift Wing
The 446th Airlift Wing is a U.S. Air Force Reserve unit that conducts strategic and tactical airlift and aeromedical evacuation missions, primarily operating C-17 Globemaster III aircraft.
-
D.
15th Air Transport Wing
The 15th Air Transport Wing is a Belgian Air Force unit responsible for strategic and tactical airlift, VIP transport, and logistical support missions.
-
E.
15th Wing
The 15th Wing is a United States Air Force unit responsible for airlift, air refueling, and operational support missions in the Pacific region.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: 167th Airlift Wing of the West Virginia Air National Guard Triple: [Martinsburg, West Virginia, hasMilitaryFacilityNearby, 167th Airlift Wing of the West Virginia Air National Guard]
Generated description
The 167th Airlift Wing of the West Virginia Air National Guard is a military airlift unit that operates transport aircraft and supports global air mobility and homeland defense missions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 167th Airlift Wing of the West Virginia Air National Guard Target entity description: The 167th Airlift Wing of the West Virginia Air National Guard is a military airlift unit that operates transport aircraft and supports global air mobility and homeland defense missions.
-
A.
62nd Airlift Wing
The 62nd Airlift Wing is a United States Air Force unit that provides global strategic airlift capabilities, primarily operating C-17 Globemaster III aircraft from Joint Base Lewis–McChord in Washington.
-
B.
89th Airlift Wing
The 89th Airlift Wing is a U.S. Air Force unit based at Joint Base Andrews that provides executive airlift support for the President, Vice President, and other senior government officials.
-
C.
446th Airlift Wing
The 446th Airlift Wing is a U.S. Air Force Reserve unit that conducts strategic and tactical airlift and aeromedical evacuation missions, primarily operating C-17 Globemaster III aircraft.
-
D.
15th Air Transport Wing
The 15th Air Transport Wing is a Belgian Air Force unit responsible for strategic and tactical airlift, VIP transport, and logistical support missions.
-
E.
15th Wing
The 15th Wing is a United States Air Force unit responsible for airlift, air refueling, and operational support missions in the Pacific region.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMilitaryFacilityNearby Context triple: [Martinsburg, West Virginia, hasMilitaryFacilityNearby, 167th Airlift Wing of the West Virginia Air National Guard]
-
A.
nearMilitaryInstallation
chosen
Indicates that one entity is located in close physical proximity to a military installation or facility.
-
B.
hasMilitaryBase
Indicates that one entity possesses, hosts, or contains a military base associated with or located on another entity.
-
C.
hasMilitaryPresence
Indicates that a military force is present in, stationed at, or operating within a particular location or entity.
-
D.
hasNearbyMilitaryHistorySite
Indicates that an entity is located close to a site of historical military significance, such as a battlefield, fort, or memorial.
-
E.
hasNearbyFacility
Indicates that one entity is located close to or in the vicinity of a particular facility.
- F. None of above.
Provenance (6 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_69a4937ae8a08190b5084a03d532b30e |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4ab4c7418819085cb64c6bf5fa70c |
completed | March 1, 2026, 9:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a76d8869888190a95857546dfae5b3 |
completed | March 3, 2026, 11:23 p.m. |
| NEDg | Description generation | batch_69a78e436c048190b31b53fff1c48f1d |
completed | March 4, 2026, 1:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a78eb80f6081908257889efaff6d33 |
completed | March 4, 2026, 1:45 a.m. |
| PD | Predicate disambiguation | batch_69a4aa73df08819096d0553a4b2509de |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:38 p.m.