Triple

T10059000
Position Surface form Disambiguated ID Type / Status
Subject Mwanza Region E208934 entity
Predicate contains P35 FINISHED
Object Mwanza City E813769 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: Mwanza City | Statement: [Mwanza Region, contains, Mwanza City]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mwanza City
Context triple: [Mwanza Region, contains, Mwanza City]
  • A. Mwanza city chosen
    Mwanza city is a major urban and commercial center on the southern shores of Lake Victoria in northern Tanzania, known for its port, fishing industry, and role as a regional hub.
  • B. Mvumbi
    Mvumbi is the Zulu name of Albert Luthuli, the South African anti-apartheid leader and Nobel Peace Prize laureate.
  • C. Orangi Town
    Orangi Town is a densely populated residential area in Karachi, Pakistan, known as one of Asia’s largest informal settlements.
  • D. Oshakati
    Oshakati is a major northern Namibian town that serves as an important commercial and administrative hub.
  • E. Egoli
    Egoli is a common nickname for Johannesburg, South Africa’s major economic hub often referred to as the "City of Gold."
  • 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_69ca836094408190a36a1ea7e9a86fcd completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cdcfb0f17c8190a8c0cfb02863537d completed April 2, 2026, 2:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2b624191c819093b8392b5573fa96 completed April 5, 2026, 7:21 p.m.
Created at: March 30, 2026, 8:57 p.m.