Triple
T29659871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jubilee Alliance |
E750375
|
entity |
| Predicate | backedPresidentialCandidate |
P167575
|
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: [Jubilee Alliance, backedPresidentialCandidate, Uhuru Kenyatta]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: backedPresidentialCandidate Context triple: [Jubilee Alliance, backedPresidentialCandidate, Uhuru Kenyatta]
-
A.
ranPresidentialCandidate
Indicates that the subject has been a candidate in a presidential election.
-
B.
partyPresidentialNomineeOf
Indicates that a person is the officially selected presidential nominee representing a particular political party.
-
C.
notablePresidentialCandidate
Indicates that a person has been a prominent or widely recognized candidate in a presidential election.
-
D.
democraticNominee
Indicates that one entity is the officially selected Democratic Party candidate for the position or role associated with the other entity.
-
E.
backedIncumbent
Indicates that a person or organization provided support to the current officeholder or existing position-holder, typically in a political or competitive context.
- F. None of above. chosen
Provenance (4 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_69f671bf54688190a920fed1847a1a9b |
completed | May 2, 2026, 9:50 p.m. |
| PD | Predicate disambiguation | batch_69f6659f246081909821c5f452d14e8f |
completed | May 2, 2026, 8:59 p.m. |
| PDg | Predicate description generation | batch_69f6691da93081909deaf680614fc900 |
completed | May 2, 2026, 9:14 p.m. |
Created at: April 28, 2026, 6:57 p.m.