Triple
T31334595
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Tanganyika via Lukuga River |
E799132
|
entity |
| Predicate | outflowDirection |
P8846
|
FINISHED |
| Object | westward |
—
|
LITERAL 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: westward | Statement: [Lake Tanganyika via Lukuga River, outflowDirection, westward]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: outflowDirection Context triple: [Lake Tanganyika via Lukuga River, outflowDirection, westward]
-
A.
outflow
Indicates the movement or discharge of something from an origin or source to the outside or to another location.
-
B.
hasDirectionOfFlow
Indicates that something moves or is transmitted from one entity or location toward another along a specific path or orientation.
-
C.
dataFlowDirection
Indicates the direction in which data moves or is transmitted from a source entity to a target entity.
-
D.
drainageDirection
chosen
Indicates the direction in which water or other fluids flow or are drained away from a given point or area.
-
E.
finalOutflowTo
Indicates the ultimate destination or receiving point to which something (such as resources, funds, or outputs) is finally transferred or discharged.
- 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.