Triple
T29659818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2017 Kenyan presidential election |
E750374
|
entity |
| Predicate | initialWinner |
P11366
|
FINISHED |
| Object | Uhuru Kenyatta |
—
|
NE NERFINISHED |
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: Uhuru Kenyatta | Statement: [2017 Kenyan presidential election, initialWinner, Uhuru Kenyatta]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialWinner Context triple: [2017 Kenyan presidential election, initialWinner, Uhuru Kenyatta]
-
A.
firstWinner
chosen
Indicates that the subject is the entity who achieved first place or victory in the referenced event or competition.
-
B.
mainWinner
Indicates that one entity is the primary or overall winner in a competition, contest, or comparative outcome relative to others.
-
C.
firstRunningWinner
Indicates that the subject is the first entity to win among those participating in a running event or race.
-
D.
winnerManager
Indicates that one entity is the manager or supervisor of another entity who is the winner in a given context or competition.
-
E.
winnerCharacter
Indicates that one entity is the character who wins or is victorious in a given event, contest, or situation involving another entity.
- 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_69f6fb19063c81909466b329655c8583 |
completed | May 3, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f6f969b4cc8190afb473a2d8b110bc |
completed | May 3, 2026, 7:29 a.m. |
Created at: April 28, 2026, 6:57 p.m.