Triple

T10652697
Position Surface form Disambiguated ID Type / Status
Subject South African politics E251009 entity
Predicate civilSocietyActor P19134 FINISHED
Object trade unions 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: trade unions | Statement: [South African politics, civilSocietyActor, trade unions]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: civilSocietyActor
Context triple: [South African politics, civilSocietyActor, trade unions]
  • A. civilSocietySupportedBy
    Indicates that a civil society organization receives backing, assistance, or resources from a specified supporter or source.
  • B. rightsOrganization
    Indicates that an entity is an organization responsible for advocating, protecting, or promoting the rights or interests of another entity.
  • C. typeOfActivist
    Indicates that one entity is an activist and specifies the particular kind or category of activism they are associated with.
  • D. advocacyOrganization chosen
    Indicates that an organization actively supports, promotes, or works on behalf of a cause, issue, or group through advocacy activities.
  • E. nonProfitSector
    Indicates that an entity operates within or is associated with the nonprofit sector, typically focusing on mission-driven rather than profit-driven activities.
  • 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_69d6aa5a4c4881908f39be6efe5981e5 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6dff78ec88190a4d1863fe87245f6 completed April 8, 2026, 11:08 p.m.
PD Predicate disambiguation batch_69d6dd8753108190b799ffa0c760526e completed April 8, 2026, 10:58 p.m.
Created at: April 8, 2026, 9:06 p.m.