Triple
T26691415
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Makuti |
E672893
|
entity |
| Predicate | hasNearbyBorderPost |
P27684
|
FINISHED |
| Object | Chirundu border post |
—
|
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: Chirundu border post | Statement: [Makuti, hasNearbyBorderPost, Chirundu border post]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyBorderPost Context triple: [Makuti, hasNearbyBorderPost, Chirundu border post]
-
A.
hasBorderPostWith
Indicates that two regions or territories share a border where an official border post or checkpoint is located between them.
-
B.
connectsToBorderPost
Indicates that one entity is linked or leads directly to a border post, establishing a route or connection between them.
-
C.
nearBorderCrossing
chosen
Indicates that an entity is located close to a border crossing point between two regions or countries.
-
D.
hasNearbyPortCountry
Indicates that one entity is a country that has a seaport located geographically close to the other entity.
-
E.
nearestInternationalBorderPostAlongPark
Indicates the closest international border checkpoint located along the boundary or within the area of a specified park.
- 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_69eecda2066c8190a344218afa5e89c1 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f791cc969c8190bf187d6031a030d5 |
completed | May 3, 2026, 6:19 p.m. |
| PD | Predicate disambiguation | batch_69f791033d288190b118029fe412b9c9 |
completed | May 3, 2026, 6:16 p.m. |
Created at: April 27, 2026, 3:26 a.m.