Triple
T11921326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karuma |
E283662
|
entity |
| Predicate | nearbyFeature |
P2064
|
FINISHED |
| Object | Karuma Falls |
E308319
|
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: Karuma Falls | Statement: [Karuma, nearbyFeature, Karuma Falls]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karuma Falls Context triple: [Karuma, nearbyFeature, Karuma Falls]
-
A.
Karuma Falls
chosen
Karuma Falls is a series of powerful rapids and waterfalls on the Victoria Nile in northern Uganda, known for its scenic beauty and nearby hydroelectric power station.
-
B.
Boyoma Falls
Boyoma Falls is a series of powerful cataracts on the Lualaba River in the Democratic Republic of the Congo, known as one of the largest waterfall systems in Africa by volume.
-
C.
Tanda Falls
Tanda Falls is a scenic waterfall and popular natural getaway located near Mirzapur in Uttar Pradesh, India.
-
D.
Zongo Falls
Zongo Falls is a scenic waterfall and popular natural attraction located in the Kongo Central Province of the Democratic Republic of the Congo.
-
E.
Diyaluma Falls
Diyaluma Falls is one of Sri Lanka’s tallest and most scenic waterfalls, renowned for its dramatic cascades and natural rock pools that attract many visitors.
- 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_69d6ab2c07e88190ba13b0d21fd6cf33 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8e8e1b08481909ed291667035f330 |
completed | April 10, 2026, 12:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f44033c288819099587af3f895eac5 |
completed | May 1, 2026, 5:54 a.m. |
Created at: April 8, 2026, 9:45 p.m.