Triple
T35391888
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KVCV |
E1022961
|
entity |
| Predicate | previousNameOfFacility |
P65
|
FINISHED |
| Object | George Air Force Base |
—
|
NE NERFINISHED |
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: George Air Force Base | Statement: [KVCV, previousNameOfFacility, George Air Force Base]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousNameOfFacility Context triple: [KVCV, previousNameOfFacility, George Air Force Base]
-
A.
formerName
chosen
Indicates that an entity was previously known by a different name in the past.
-
B.
formerSiteName
Indicates that an entity previously had a different site name, specifying what that earlier name was.
-
C.
previousNameUsedUntil
Indicates that a particular name was used for an entity up to (but not necessarily including) a specified end date or time.
-
D.
tenantFormerName
Indicates that the specified name was previously used by the tenant before their current official name.
-
E.
venueFormerName
Indicates that a venue previously had a different official name than it has currently.
- 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_69f76df34ba48190bd80f0814cdcd540 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff63225b6481909217ad11b4f7d3ba |
completed | May 9, 2026, 4:38 p.m. |
| PD | Predicate disambiguation | batch_69ff60e0882c819085d097010db43ee0 |
completed | May 9, 2026, 4:29 p.m. |
Created at: May 3, 2026, 4:03 p.m.