Triple

T28025660
Position Surface form Disambiguated ID Type / Status
Subject 2019 South African general election E708115 entity
Predicate DAVoteSharePercentage P163182 FINISHED
Object about 20.8% 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: about 20.8% | Statement: [2019 South African general election, DAVoteSharePercentage, about 20.8%]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: DAVoteSharePercentage
Context triple: [2019 South African general election, DAVoteSharePercentage, about 20.8%]
  • A. DAVoteSharePercentage chosen
    Indicates the percentage of total votes that were cast in favor of the specified entity in a given election or voting event.
  • B. DVPVoteShare
    Indicates the proportion of total votes that were cast for the DVP party in an election.
  • C. IFPVoteSharePercentage
    Indicates the percentage of total votes received that were cast for the IFP (Inkatha Freedom Party) in a given election or voting context.
  • D. hasVotingPowerPerShare
    Indicates that an entity possesses a specified amount of voting power associated with each individual share it holds.
  • E. hasVotingStake
    Indicates that one entity possesses a share of voting power or decision-making authority in 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_69ef9b6bdd9c8190bb3a574a03774ad1 completed April 27, 2026, 5:22 p.m.
NER Named-entity recognition batch_69f63c6e32588190a158f8e20946b582 completed May 2, 2026, 6:03 p.m.
PD Predicate disambiguation batch_69f63710d17c819084cfe96e6df334fd completed May 2, 2026, 5:40 p.m.
Created at: April 27, 2026, 8:12 p.m.