Triple

T20354402
Position Surface form Disambiguated ID Type / Status
Subject Southern Tanzania E496103 entity
Predicate hasCity P316 FINISHED
Object Iringa 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: Iringa | Statement: [Southern Tanzania, hasCity, Iringa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Iringa
Context triple: [Southern Tanzania, hasCity, Iringa]
  • A. Nyamwezi
    Nyamwezi is a Bantu language spoken primarily in northwestern Tanzania by the Nyamwezi people.
  • 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. Mikocheni
    Mikocheni is a residential and commercial neighborhood in Dar es Salaam, Tanzania, known for its middle-class housing, offices, and educational institutions.
  • D. Mbeya
    Mbeya is a major city in southwestern Tanzania, serving as a commercial and transport hub near the Zambian border.
  • E. Iringa Region chosen
    Iringa Region is an administrative area in south-central Tanzania known for its highland landscapes and as the gateway to Ruaha National Park, one of the country’s largest wildlife reserves.
  • 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_69e0b4a3f7f48190b37f354574028ca6 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67852ca9881908a5af18005639859 completed April 20, 2026, 7:02 p.m.
Created at: April 16, 2026, 11:25 a.m.