Triple
T34915343
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Africa–Botswana border |
E1006984
|
entity |
| Predicate | borderingCountryOfBotswana |
P198845
|
FINISHED |
| Object | South Africa |
—
|
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: South Africa | Statement: [South Africa–Botswana border, borderingCountryOfBotswana, South Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderingCountryOfBotswana Context triple: [South Africa–Botswana border, borderingCountryOfBotswana, South Africa]
-
A.
hasBorderTownOnZambianSide
Indicates that a town is located on the Zambian side of a border shared with another country.
-
B.
borderTypeWithSouthAfrica
Indicates the type or nature of the border that an entity shares with South Africa.
-
C.
nearbyCountryTownOnNamibiaSide
Indicates that a town is located near a country border and lies on the side belonging to Namibia.
-
D.
governingAuthoritySideBotswana
Indicates that the referenced party is aligned with, represents, or acts on behalf of the governing authority of Botswana in a given context or dispute.
-
E.
hasCountryBorderWith
chosen
Indicates that two countries share a common land or maritime boundary.
- 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_69f76dc2b6b0819095a61debbd405269 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff891e4b9c8190aa86a339a8944496 |
completed | May 9, 2026, 7:21 p.m. |
| PD | Predicate disambiguation | batch_69ff8801180c8190b23e20996ca68e0a |
completed | May 9, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4 p.m.