Triple
T1840004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 36th Wing |
E41153
|
entity |
| Predicate | hostUnitFor |
P3556
|
FINISHED |
| Object | Andersen Air Force Base tenant units |
—
|
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: Andersen Air Force Base tenant units | Statement: [36th Wing, hostUnitFor, Andersen Air Force Base tenant units]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostUnitFor Context triple: [36th Wing, hostUnitFor, Andersen Air Force Base tenant units]
-
A.
hostsUnit
chosen
Indicates that one entity serves as the location or container in which another unit is situated, operates, or is organized.
-
B.
hostsUnitType
Indicates that one entity serves as a location or platform that accommodates or contains a specified type of unit.
-
C.
hubFor
Indicates that one entity serves as a central node or focal point through which activities, connections, or resources related to another entity are organized or routed.
-
D.
hostsCompany
Indicates that one entity provides space, infrastructure, or support for a company to operate, be located, or hold activities.
-
E.
host
Indicates that one entity provides space, resources, or services to accommodate, receive, or entertain another entity.
- 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_69a88647f9388190909bc36e795bdaec |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb32d35508190bf1c487dffbecaf0 |
completed | March 7, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69abafd88ebc81908208394746351fe6 |
completed | March 7, 2026, 4:55 a.m. |
Created at: March 4, 2026, 7:33 p.m.