Triple
T20072509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Havu |
E499772
|
entity |
| Predicate | usesWaterBodyFor |
P44236
|
FINISHED |
| Object | transport on Lake Kivu |
—
|
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: transport on Lake Kivu | Statement: [Havu, usesWaterBodyFor, transport on Lake Kivu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesWaterBodyFor Context triple: [Havu, usesWaterBodyFor, transport on Lake Kivu]
-
A.
appliesToWaterBody
Indicates that something (such as a rule, condition, property, or effect) is relevant or applicable specifically to a particular water body.
-
B.
involvesBodyOfWater
Indicates that the relationship or event includes, affects, or takes place in connection with a body of water such as a sea, lake, river, or ocean.
-
C.
navigatesWaterBody
Indicates that an entity moves through or across a body of water as a means of travel or operation.
-
D.
waterbodyUsedFor
chosen
Indicates that a particular water body is utilized for a specific purpose, activity, or function.
-
E.
locatedOnWaterbody
Indicates that an entity is situated on or directly adjacent to a specified body of water.
- 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e664392c748190a6cc472f80b8c74b |
completed | April 20, 2026, 5:36 p.m. |
| PD | Predicate disambiguation | batch_69e54cf369b88190931532420517dac7 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:40 p.m.