Triple
T14977459
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Highlands, California |
E373487
|
entity |
| Predicate | formerNearbyInstallationUse |
P51359
|
FINISHED |
| Object | United States Air Force base |
—
|
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: United States Air Force base | Statement: [North Highlands, California, formerNearbyInstallationUse, United States Air Force base]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerNearbyInstallationUse Context triple: [North Highlands, California, formerNearbyInstallationUse, United States Air Force base]
-
A.
hasFormerUseNearby
chosen
Indicates that something in the vicinity previously had a particular use or function that is no longer current.
-
B.
hasNearbyInstallation
Indicates that one entity has another installation or facility located close to it in physical space.
-
C.
locatedNearFormer
Indicates that one entity is situated close to another entity that previously occupied a nearby or the same location.
-
D.
formerNameOfContainedInstallation
Indicates that an installation previously had a different name while remaining the same contained installation.
-
E.
usedByNearbyTownFor
Indicates that something serves a function or purpose for a town located in close geographic proximity.
- 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_69d85ccbbcd48190acb56e7cf104d8ad |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6fbd138819092254ea37388026c |
completed | April 15, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69de9a5d995881909e33658f5aea5582 |
completed | April 14, 2026, 7:49 p.m. |
Created at: April 10, 2026, 2:51 a.m.