Triple

T5181949
Position Surface form Disambiguated ID Type / Status
Subject South Kivu E116941 entity
Predicate largestCity P235 FINISHED
Object Bukavu E482939 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: Bukavu | Statement: [South Kivu, largestCity, Bukavu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bukavu
Context triple: [South Kivu, largestCity, Bukavu]
  • A. Bukavu chosen
    Bukavu is a major city in the eastern Democratic Republic of the Congo, located on the southwestern shore of Lake Kivu near the Rwandan border.
  • B. Gitega
    Gitega is the political and administrative capital city of Burundi, located in the central part of the country.
  • C. Kigali
    Kigali is the capital and largest city of Rwanda, known as a major political and economic hub in East Africa.
  • D. Mbandaka
    Mbandaka is a city in the northwestern Democratic Republic of the Congo, located on the Congo River and serving as a regional commercial and administrative center.
  • E. Butembo
    Butembo is a major commercial city in eastern Democratic Republic of the Congo, known as a trading hub and economic center in North Kivu.
  • 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_69bd446140f08190becb93c61158f27f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd799bc58c819098a8e91e21baaef4 completed March 20, 2026, 4:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69bee07d20208190a423a9a395ac9d32 completed March 21, 2026, 6:16 p.m.
Created at: March 20, 2026, 1:45 p.m.