Triple
T26352808
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fish River Canyon |
E662945
|
entity |
| Predicate | borderingCountryOfPark |
P22471
|
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: [Fish River Canyon, borderingCountryOfPark, South Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderingCountryOfPark Context triple: [Fish River Canyon, borderingCountryOfPark, South Africa]
-
A.
bordersNationalPark
chosen
Indicates that one entity shares a boundary or edge directly with a national park.
-
B.
borderingCountryNearby
Indicates that one country is geographically close to, but does not necessarily share a direct land border with, another country.
-
C.
hasCountryPark
Indicates that a place or administrative area contains or is associated with a designated country park.
-
D.
countryBorderFeatureOf
Indicates that a geographical feature (such as a river, mountain range, or coastline) serves as or is part of the border of a country.
-
E.
partOfTransfrontierConservationArea
Indicates that an entity is included within or belongs to a transfrontier conservation area that spans across national or regional boundaries.
- 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_69ee8130fc44819094e5ab1da201cd7b |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f7688dd3d08190ad13d0e780570a1c |
completed | May 3, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69f767fcf2f881908bacc7bfc38e68a5 |
completed | May 3, 2026, 3:21 p.m. |
Created at: April 26, 2026, 10:46 p.m.