Triple
T10887152
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zimbabwean general election, 2018 |
E257077
|
entity |
| Predicate | votingSystemPresidential |
P539
|
FINISHED |
| Object | two-round system |
—
|
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: two-round system | Statement: [Zimbabwean general election, 2018, votingSystemPresidential, two-round system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: votingSystemPresidential Context triple: [Zimbabwean general election, 2018, votingSystemPresidential, two-round system]
-
A.
presidentialVote
Indicates that an entity casts or records a vote in a presidential election for a particular candidate or option.
-
B.
electionMethod
chosen
Indicates the process or system used to select a candidate or make a decision in an election.
-
C.
presidencySelection
Indicates the process or outcome by which an individual is chosen or appointed to hold the office of the presidency.
-
D.
typicalPresidentialVote
Indicates that the vote cast aligns with the usual or characteristic voting pattern observed in presidential elections.
-
E.
electionSystemFeature
Indicates that an election system possesses a specific characteristic, mechanism, or procedural feature related to how elections are conducted or managed.
- 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_69d6aa848804819081b2713ca0bedf06 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d75201e6888190a2bc41a17784eec3 |
completed | April 9, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69d70d3943c881908895397eccc3e415 |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:21 p.m.