Triple

T23034103
Position Surface form Disambiguated ID Type / Status
Subject Gukurahundi E573546 entity
Predicate location P40 FINISHED
Object Midlands Province 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: Midlands Province | Statement: [Gukurahundi, location, Midlands Province]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Midlands Province
Context triple: [Gukurahundi, location, Midlands Province]
  • A. Midlands Province chosen
    Midlands Province is a central region of Zimbabwe known for its mining activities and agricultural production, with Gweru as its capital city.
  • B. North Province
    North Province is a geographic region situated adjacent to South Province, forming part of a larger administrative or territorial division.
  • C. Mashonaland Central Province
    Mashonaland Central Province is a predominantly rural administrative region in northern Zimbabwe known for its agriculture and proximity to the capital, Harare.
  • D. North Eastern Province
    North Eastern Province was a former administrative region in Kenya known for its arid climate, predominantly Somali population, and long border with Somalia.
  • E. Matabeleland
    Matabeleland is a historical region in southwestern Zimbabwe, traditionally inhabited by the Ndebele people and centered around the city of Bulawayo.
  • 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_69e245b911188190bc3d96326c847969 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18483e5848190977b1bdb1b83d187 completed April 29, 2026, 4:09 a.m.
Created at: April 17, 2026, 3:53 p.m.