Triple
T3212179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ngonye Falls |
E67304
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Sioma Falls |
E67304
|
NE FINISHED |
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: Sioma Falls | Statement: [Ngonye Falls, alsoKnownAs, Sioma Falls]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sioma Falls Context triple: [Ngonye Falls, alsoKnownAs, Sioma Falls]
-
A.
Itanda Falls
Itanda Falls is a powerful series of white-water rapids on the Victoria Nile in Uganda, popular for rafting and kayaking.
-
B.
Mutarazi Falls
Mutarazi Falls is one of Zimbabwe’s tallest and most spectacular waterfalls, plunging dramatically down the edge of the Eastern Highlands.
-
C.
Uhuru Falls
Uhuru Falls is a powerful waterfall in northwestern Uganda located near Murchison Falls on the Nile River, known for its dramatic cascades and scenic surroundings.
-
D.
Ngonye Falls
chosen
Ngonye Falls is a broad, horseshoe-shaped waterfall on the Zambezi River in western Zambia, noted for its scenic beauty and less-developed, remote setting compared to Victoria Falls.
-
E.
Lugard Falls
Lugard Falls is a series of spectacular white-water rapids and eroded rock formations on the Galana River in Kenya, known for its dramatic scenery and wildlife viewing.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad858ac36c81909962589cd277d6e2 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaaba224c8190ad2f4e0ed1c2ca4a |
completed | March 8, 2026, 4:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2771204e0819086ae2838a368589a |
completed | March 12, 2026, 8:19 a.m. |
Created at: March 8, 2026, 3:07 p.m.