Triple

T11123744
Position Surface form Disambiguated ID Type / Status
Subject Lobatse E263081 entity
Predicate currency P245 FINISHED
Object Botswana pula E6376 NE 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: Botswana pula | Statement: [Lobatse, currency, Botswana pula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Botswana pula
Context triple: [Lobatse, currency, Botswana pula]
  • A. Botswana pula chosen
    The Botswana pula is the official currency of Botswana, known for its relative stability and use in some cross-border transactions in Southern Africa.
  • B. Namibian dollar
    The Namibian dollar is the official national currency of Namibia, pegged at par to the South African rand and used alongside it in everyday transactions.
  • C. Zimbabwean dollar
    The Zimbabwean dollar was the former national currency of Zimbabwe, notorious for its extreme hyperinflation before being abandoned in favor of foreign currencies.
  • D. South African pound
    The South African pound was the former currency of South Africa, used before the country adopted the decimalized rand in 1961.
  • E. Zambian kwacha
    The Zambian kwacha is the official fiat currency of Zambia, used for everyday transactions and issued by the Bank of Zambia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d6aa9b46cc8190b19f9f0cc45bf322 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7e82e933481908550499cf9dd6531 completed April 9, 2026, 5:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69e441d376f8819080effd5bf29c6bc1 completed April 19, 2026, 2:45 a.m.
Created at: April 8, 2026, 9:28 p.m.