Triple
T18896495
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Francis Muthaura |
E462221
|
entity |
| Predicate | appointedBy |
P257
|
FINISHED |
| Object | Mwai Kibaki |
—
|
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: Mwai Kibaki | Statement: [Francis Muthaura, appointedBy, Mwai Kibaki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mwai Kibaki Context triple: [Francis Muthaura, appointedBy, Mwai Kibaki]
-
A.
Mwai Kibaki
chosen
Mwai Kibaki was a Kenyan economist and politician who served as the third President of Kenya from 2002 to 2013.
-
B.
William Ruto
William Ruto is a Kenyan politician who serves as the country’s president and has long been a prominent figure in its national politics.
-
C.
Francis Muthaura
Francis Muthaura is a Kenyan diplomat and civil servant who became a prominent regional figure through his leadership roles in East African and national government institutions.
-
D.
Uhuru Kenyatta
Uhuru Kenyatta is a Kenyan politician who served as the fourth President of Kenya from 2013 to 2022.
-
E.
Lucy Kibaki
Lucy Kibaki was the former First Lady of Kenya, known for her outspoken personality and her role as the wife of President Mwai Kibaki.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcfd05bc819088903cca13cc2846 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c47f6c948190918ade08bb88f1fd |
completed | April 20, 2026, 6:15 a.m. |
Created at: April 10, 2026, 11:58 a.m.