Triple

T8309666
Position Surface form Disambiguated ID Type / Status
Subject Kagera Region E194558 entity
Predicate capital P234 FINISHED
Object Bukoba E637685 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: Bukoba | Statement: [Kagera Region, capital, Bukoba]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bukoba
Context triple: [Kagera Region, capital, Bukoba]
  • A. Bukoba chosen
    Bukoba is a town on the western shore of Lake Victoria in northwestern Tanzania, serving as the capital of the Kagera Region and a local transport and trade hub.
  • B. Kigoma
    Kigoma is a port city in western Tanzania located on the eastern shore of Lake Tanganyika and serving as a key regional transport and trade hub.
  • C. Uvira
    Uvira is a city in the eastern Democratic Republic of the Congo, located on the northern shores of Lake Tanganyika near the border with Burundi.
  • D. Namutoni
    Namutoni is a historic former German fort turned tourist rest camp and lodge located on the eastern side of Etosha National Park in Namibia.
  • E. Nyamwezi
    Nyamwezi is a Bantu language spoken primarily in northwestern Tanzania by the Nyamwezi people.
  • 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_69ca82e613e88190bf8139669bbd0d53 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7f2d2c30819095075940479b75a7 completed March 31, 2026, 8 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd95665390819089c8becad018cf51 completed April 1, 2026, 10 p.m.
Created at: March 30, 2026, 5:54 p.m.