Triple
T21482710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lisbon Falls |
E530034
|
entity |
| Predicate | nearbyTown |
P3883
|
FINISHED |
| Object | Sabie |
—
|
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: Sabie | Statement: [Lisbon Falls, nearbyTown, Sabie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sabie Context triple: [Lisbon Falls, nearbyTown, Sabie]
-
A.
Sabie
chosen
Sabie is a small forestry and tourism town in northeastern South Africa, known as a gateway to waterfalls and scenic routes near the Drakensberg escarpment.
-
B.
Mzima Springs
Mzima Springs is a series of natural freshwater springs in Kenya renowned for their clear waters, hippos, crocodiles, and underwater viewing platforms within Tsavo National Park.
-
C.
Ngqumbazi
Ngqumbazi was a Zulu royal woman best known as the mother of King Cetshwayo kaMpande of the Zulu Kingdom.
-
D.
Nxai Pan
Nxai Pan is a vast salt pan and seasonal wildlife area in northeastern Botswana, renowned for its open grasslands, baobab trees, and large migrations of zebras and other game.
-
E.
Thohoyandou
Thohoyandou is a town in South Africa’s Limpopo province that serves as an administrative, commercial, and educational hub for the surrounding region.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea34c4388190adc78d209d2aafb8 |
completed | April 23, 2026, 9:45 a.m. |
Created at: April 16, 2026, 6:21 p.m.