Triple
T37410215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Busia District |
E929542
|
entity |
| Predicate | borderPostRole |
P113300
|
FINISHED |
| Object | customs and immigration control point between Kenya and Uganda |
—
|
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: customs and immigration control point between Kenya and Uganda | Statement: [Busia District, borderPostRole, customs and immigration control point between Kenya and Uganda]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderPostRole Context triple: [Busia District, borderPostRole, customs and immigration control point between Kenya and Uganda]
-
A.
borderPostIs
Indicates that one entity functions as a border post associated with or located at another entity.
-
B.
borderPostType
Indicates the specific kind or classification of a border post associated with a boundary or crossing point.
-
C.
borderPostHandles
chosen
Indicates that a particular border post is responsible for managing, processing, or overseeing a specified type of traffic, activity, or operation.
-
D.
borderPostName
Indicates the specific name assigned to a border post where a boundary crossing or checkpoint is located.
-
E.
borderPass
Indicates that one entity crosses or moves through the boundary separating two regions or jurisdictions.
- 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_69f76ebde49481908566cd96b37ccc84 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a0008225cc081909ff1fd0639859dc4 |
completed | May 10, 2026, 4:22 a.m. |
| PD | Predicate disambiguation | batch_6a0007bac5d8819098aff8031d4abe5d |
completed | May 10, 2026, 4:21 a.m. |
Created at: May 3, 2026, 4:16 p.m.