Triple
T25275941
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tunduma–Nakonde border |
E633695
|
entity |
| Predicate | roadCrossingBetween |
P158321
|
FINISHED |
| Object | Zambia |
—
|
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: Zambia | Statement: [Tunduma–Nakonde border, roadCrossingBetween, Zambia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roadCrossingBetween Context triple: [Tunduma–Nakonde border, roadCrossingBetween, Zambia]
-
A.
roadCrossingBetween
chosen
Indicates that a road crossing (such as a crosswalk or intersection crossing) exists between two locations or road segments, connecting them for passage across the road.
-
B.
railCrossingBetween
Indicates that a railway crossing is located between two specified entities or locations, connecting or intersecting them.
-
C.
mainRoadCrossingBetween
Indicates that a primary or main road intersects or passes between two specified locations or entities.
-
D.
crossedByHighway
Indicates that a highway passes across or through the extent of a given entity or area.
-
E.
crossesStreet
Indicates that an entity moves from one side of a street to the other, traversing the street’s width.
- 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_69e75a92f48881909974ff9c11150a2e |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f48ba6156481909e0b7e9965b4bc48 |
completed | May 1, 2026, 11:16 a.m. |
| PD | Predicate disambiguation | batch_69f4683472ec8190a483b3b8afe71720 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 1:17 p.m.