Triple
T31334602
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Tanganyika via Lukuga River |
E799132
|
entity |
| Predicate | linksBasin |
P164428
|
FINISHED |
| Object | Lake Tanganyika basin |
—
|
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 basin | Statement: [Lake Tanganyika via Lukuga River, linksBasin, Lake Tanganyika basin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linksBasin Context triple: [Lake Tanganyika via Lukuga River, linksBasin, Lake Tanganyika basin]
-
A.
resourceBasin
Indicates a relationship where a basin serves as a source or reservoir of resources for another entity or area.
-
B.
basinInteractsWith
chosen
Indicates that one basin affects or exchanges material, energy, or influence with another basin through some form of interaction.
-
C.
sourceBasin
Indicates that one entity is the drainage basin or watershed from which another entity (such as a river segment or water body) originates or receives its source waters.
-
D.
formsBasinWith
Indicates that one geographic feature combines with another to create or define a shared basin or catchment area.
-
E.
basinSystem
Indicates a relationship where one entity functions as or belongs to a basin system associated with another entity.
- 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_69f224e3f6ac8190a13488516abca7c9 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69ee3cfb881908234c228855d154d |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d1d25e88190a7f57d323574da90 |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:16 p.m.