Triple
T28361251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kenya (former provinces system) |
E718367
|
entity |
| Predicate | higherLevelUnitOf |
P89327
|
FINISHED |
| Object | districts |
—
|
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: districts | Statement: [Kenya (former provinces system), higherLevelUnitOf, districts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: higherLevelUnitOf Context triple: [Kenya (former provinces system), higherLevelUnitOf, districts]
-
A.
higherLevelDivision
Indicates that one administrative or organizational unit is a parent or superior division relative to another, lower-level unit.
-
B.
superunitOf
chosen
Indicates that one unit is hierarchically above and directly encompasses another unit within an organizational or structural system.
-
C.
upperLevels
Indicates that one entity occupies or corresponds to higher levels, tiers, or hierarchical positions relative to another entity.
-
D.
hasHigherLevelRegion
Indicates that one region is geographically or administratively contained within and subordinate to a larger, higher-level region.
-
E.
higherLevelBody
Indicates that one body or organizational unit functions at a higher or more encompassing level of authority or structure relative to another.
- 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_69eff6ed5af48190be4e0adf298223e0 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f6d0d46aec819091edf97324d793ac |
completed | May 3, 2026, 4:36 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe2183481908ae4e85a59c66f69 |
completed | May 3, 2026, 4:32 a.m. |
Created at: April 28, 2026, 12:52 a.m.