Triple
T20443253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kalehe Territory |
E501448
|
entity |
| Predicate | locatedOppositeAcrossWaterbody |
P64456
|
FINISHED |
| Object | Rwanda 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: Rwanda on Lake Kivu | Statement: [Kalehe Territory, locatedOppositeAcrossWaterbody, Rwanda on Lake Kivu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedOppositeAcrossWaterbody Context triple: [Kalehe Territory, locatedOppositeAcrossWaterbody, Rwanda on Lake Kivu]
-
A.
bodyOfWaterOnOtherSide
Indicates that one entity is located across a body of water from the other entity, with the water lying between them.
-
B.
locatedAcrossRiverFrom
Indicates that one entity is situated on the opposite side of a river relative to another entity.
-
C.
acrossWaterFrom
chosen
Indicates that two entities are located on opposite sides of a body of water, separated by that water.
-
D.
nearestCityAcrossWater
Indicates that one city is the closest city to another city when considering only routes or separation across a body of water.
-
E.
separatedFromByWaterBody
Indicates that two entities are apart from each other with a body of water lying between them as the separating barrier.
- 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_69e0b4ac0a1c81908845d0f8a56abce8 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e68cfa7dd08190883a37e3480b152c |
completed | April 20, 2026, 8:30 p.m. |
| PD | Predicate disambiguation | batch_69e5766df0008190a73c4f613c29678f |
completed | April 20, 2026, 12:42 a.m. |
Created at: April 16, 2026, 11:32 a.m.