Triple
T33611441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siavonga–Kariba crossing |
E860996
|
entity |
| Predicate | borderSideCountry |
P70148
|
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: [Siavonga–Kariba crossing, borderSideCountry, Zambia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderSideCountry Context triple: [Siavonga–Kariba crossing, borderSideCountry, Zambia]
-
A.
borderCountrySide
chosen
Indicates that one country shares a land border with the side or region of another country.
-
B.
countryBorderType
Indicates the type or nature of the border relationship that exists between two countries.
-
C.
nationalBorder
Indicates that two geographic or political entities share a common national boundary separating their territories.
-
D.
borderRegime
Indicates the type, rules, or control system governing how movement or interaction is managed across a border between entities.
-
E.
borderCultureWith
Indicates that two regions or entities share a common boundary across which cultural traits, practices, or influences are actively exchanged or intertwined.
- 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_69f3498037c88190a4500f002b5540e0 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff409ff5548190849c2d50e99bd807 |
completed | May 9, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69ff401a5e188190a72f945e910b4a6c |
completed | May 9, 2026, 2:09 p.m. |
Created at: May 1, 2026, 1:41 a.m.