Triple
T29659834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2017 Kenyan presidential election |
E750374
|
entity |
| Predicate | repeatElectionTurnout |
P1235
|
FINISHED |
| Object | significantly lower than August poll |
—
|
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: significantly lower than August poll | Statement: [2017 Kenyan presidential election, repeatElectionTurnout, significantly lower than August poll]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: repeatElectionTurnout Context triple: [2017 Kenyan presidential election, repeatElectionTurnout, significantly lower than August poll]
-
A.
repeatElectionTimeLimit
Indicates that there is a specified time limit within which an election may be repeated or rerun.
-
B.
reElectionOf
Indicates that an entity is being elected again to a position or office they have previously held.
-
C.
portionUpForElectionEachCycle
Indicates what fraction of the total membership or seats is contested in each election cycle.
-
D.
voterTurnoutChange
chosen
Indicates the amount or direction of change in voter turnout between two elections or time periods.
-
E.
reElectionType
Indicates the specific manner or category of re-election associated with a given officeholder or electoral event.
- 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_69f0d6226fe881908819197c9ef9ee04 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f67d3624248190a36a9b2d2e9778d4 |
completed | May 2, 2026, 10:39 p.m. |
| PD | Predicate disambiguation | batch_69f678ce54b081908c26edfd49e39c60 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 28, 2026, 6:57 p.m.