Triple
T28271703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nkasi |
E712872
|
entity |
| Predicate | bodyOfWaterNearby |
P49291
|
FINISHED |
| Object | Lake Tanganyika |
—
|
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 Tanganyika | Statement: [Nkasi, bodyOfWaterNearby, Lake Tanganyika]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodyOfWaterNearby Context triple: [Nkasi, bodyOfWaterNearby, Lake Tanganyika]
-
A.
hasNearbyWater
chosen
Indicates that one entity is located close to a body of water associated with or relevant to another entity.
-
B.
nearestLargeBodyOfWater
Indicates the closest significant body of water in proximity to a given location or entity.
-
C.
waterBodyCreatedNearby
Indicates that a water body has been formed or established in close spatial proximity to a specified reference location or entity.
-
D.
lakeTypeNearby
Indicates that one entity is located near another entity that is classified as a particular type of lake.
-
E.
nearbyWatercourse
Indicates that one entity is located close to or alongside a natural or artificial watercourse, such as a river, stream, or canal.
- 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_69efb5216c6881908020dce4aea65381 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f64447b738819088589cca5312c4e8 |
completed | May 2, 2026, 6:36 p.m. |
| PD | Predicate disambiguation | batch_69f641e0fde08190bf06a1c5b388aa84 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 27, 2026, 11:18 p.m.