Triple

T22335394
Position Surface form Disambiguated ID Type / Status
Subject Soshangane E552132 entity
Predicate regionOfActivity P82 FINISHED
Object eastern Zimbabwe 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: eastern Zimbabwe | Statement: [Soshangane, regionOfActivity, eastern Zimbabwe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: eastern Zimbabwe
Context triple: [Soshangane, regionOfActivity, eastern Zimbabwe]
  • A. eastern Zimbabwe chosen
    Eastern Zimbabwe is a region of Zimbabwe characterized by its mountainous terrain, lush valleys, and proximity to the border with Mozambique.
  • B. southeastern Zimbabwe
    Southeastern Zimbabwe is a predominantly rural region of Zimbabwe that includes the historic city of Masvingo and parts of the country’s lowveld and Great Zimbabwe heritage area.
  • C. Northern Zimbabwe
    Northern Zimbabwe is a region of Zimbabwe that includes part of the ancestral and cultural homeland of the Tonga people of southern Africa.
  • D. south-western Zimbabwe
    South-western Zimbabwe is a historical region of Zimbabwe that formed the heartland of the Ndebele kingdom established in the 19th century.
  • E. northwestern Zimbabwe
    Northwestern Zimbabwe is a sparsely populated region characterized by rugged plateaus, river valleys, and significant wildlife habitats, including major protected areas and national parks.
  • 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_69e11e494eec81909c4d2d51f69499d9 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1577e35f48190b11789d80182653e completed April 29, 2026, 12:57 a.m.
Created at: April 16, 2026, 8:43 p.m.