Triple
T33483567
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2006 Ugandan general election |
E857546
|
entity |
| Predicate | hasMainCandidate |
P1221
|
FINISHED |
| Object | Yoweri Museveni |
—
|
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: Yoweri Museveni | Statement: [2006 Ugandan general election, hasMainCandidate, Yoweri Museveni]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMainCandidate Context triple: [2006 Ugandan general election, hasMainCandidate, Yoweri Museveni]
-
A.
hasMainProponent
Indicates that one entity is the primary advocate, champion, or leading supporter of another entity.
-
B.
mainCandidates
chosen
Indicates that the referenced entities are the primary or most prominent candidates within a given selection or context.
-
C.
hasMainRepresentative
Indicates that one entity serves as the primary or official representative of another entity.
-
D.
hasMajorPartyCandidate
Indicates that an election, race, or contest includes at least one candidate representing a major political party.
-
E.
hasMainResult
Indicates that one entity is the primary or most significant outcome, conclusion, or result produced by another entity or process.
- 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_69f3497547608190a1a0f2365fb713ee |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a011d76f3f88190be3d7c9eb0552f34 |
completed | May 11, 2026, 12:06 a.m. |
| PD | Predicate disambiguation | batch_6a011cce684881909dd15776bb77a6e0 |
completed | May 11, 2026, 12:03 a.m. |
Created at: May 1, 2026, 1:38 a.m.