Triple

T19891591
Position Surface form Disambiguated ID Type / Status
Subject Central Province, Zambia E478043 entity
Predicate hasTown P847 FINISHED
Object Mkushi 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: Mkushi | Statement: [Central Province, Zambia, hasTown, Mkushi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mkushi
Context triple: [Central Province, Zambia, hasTown, Mkushi]
  • A. Mkushi chosen
    Mkushi is a farming and trading town in Zambia known for its commercial agriculture, particularly large-scale commercial farming.
  • B. Mankwe
    Mankwe is a locality in South Africa, historically part of the former Bophuthatswana homeland in the North West Province.
  • C. Mumbwa
    Mumbwa is a town in central Zambia known as an agricultural and mining hub west of the capital, Lusaka.
  • D. Moyo
    Moyo is a town in northern Uganda that serves as an administrative and commercial center near the border with South Sudan.
  • E. Moyo
    Moyo is a dialect of the Madi language spoken by the Madi people of Central Africa, particularly in parts of South Sudan and Uganda.
  • 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_69d8e51f32b08190b3687f4f60353250 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6590ed7988190bc6b610d1f4fa194 completed April 20, 2026, 4:49 p.m.
Created at: April 10, 2026, 1:52 p.m.