Triple
T13445782
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mzima Springs |
E320477
|
entity |
| Predicate | distanceFromVoi_km |
P22795
|
FINISHED |
| Object | approximately 48 |
—
|
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: approximately 48 | Statement: [Mzima Springs, distanceFromVoi_km, approximately 48]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceFromVoi_km Context triple: [Mzima Springs, distanceFromVoi_km, approximately 48]
-
A.
distancedFrom
Indicates that one entity is physically or metaphorically kept at a certain distance or separation from another entity.
-
B.
depthApproxKm
Indicates the approximate depth of something measured in kilometers.
-
C.
distanceFromReading
Indicates the measured spatial distance between a specified entity and the location of Reading.
-
D.
distanceFromCentre
Indicates the measured or specified distance of an entity from a defined central point.
-
E.
approximateDistanceKm
chosen
Indicates the estimated distance between two entities measured in kilometers, typically with some degree of inaccuracy or approximation.
- 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_69d80761e6cc8190a90c844589998ecc |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbaef5f610819092cad33ef72075ff |
completed | April 12, 2026, 2:40 p.m. |
| PD | Predicate disambiguation | batch_69d9a03ce03481908c61094f0cc0c158 |
completed | April 11, 2026, 1:13 a.m. |
Created at: April 9, 2026, 9:40 p.m.