Triple
T23016636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gisenyi |
E573046
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Lake Kivu |
—
|
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: Lake Kivu | Statement: [Gisenyi, locatedOn, Lake Kivu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lake Kivu Context triple: [Gisenyi, locatedOn, Lake Kivu]
-
A.
Lake Kivu
chosen
Lake Kivu is a large freshwater lake on the border between Rwanda and the Democratic Republic of the Congo, notable for its scenic volcanic surroundings and vast reserves of dissolved methane gas.
-
B.
Lake Burera
Lake Burera is a scenic freshwater lake in northern Rwanda, known for its volcanic highland setting near the Ugandan border and its proximity to Lake Ruhondo and the Virunga Mountains.
-
C.
Lake Rwanyakizinga
Lake Rwanyakizinga is a freshwater lake in eastern Rwanda that forms part of the wetland and savanna landscape within Akagera National Park.
-
D.
Lake Kyoga
Lake Kyoga is a large, shallow freshwater lake in central Uganda that forms part of the Nile River system and supports important fisheries, wetlands, and local transportation.
-
E.
Kivu
Kivu is a conflict-affected region in eastern Democratic Republic of the Congo known for its rich natural resources, humanitarian crises, and recurrent outbreaks of violence and disease.
- 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e59a1c8190b8048a399a4727cb |
completed | April 29, 2026, 4:07 a.m. |
Created at: April 17, 2026, 3:52 p.m.