Triple

T2103737
Position Surface form Disambiguated ID Type / Status
Subject Uvinza E37146 entity
Predicate connectedTo P37 FINISHED
Object Kigoma E34026 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: Kigoma | Statement: [Uvinza, connectedTo, Kigoma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kigoma
Context triple: [Uvinza, connectedTo, Kigoma]
  • A. Kigoma chosen
    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.
  • B. Kigoma Region
    Kigoma Region is a western Tanzanian administrative region along Lake Tanganyika, known for its biodiversity and as a center for primate research.
  • C. South Kivu
    South Kivu is a conflict-affected province in the eastern Democratic Republic of the Congo, known for its ethnic tensions, mineral wealth, and presence of numerous armed groups.
  • D. Kibondo
    Kibondo is a town in western Tanzania that serves as an administrative and commercial center in the Kigoma Region.
  • E. Rukwa Valley
    Rukwa Valley is a region in southwestern Tanzania known for its fertile lowlands, proximity to Lake Rukwa, and as a traditional homeland of several ethnic groups including the Fipa 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_69a8861828948190924aa30c08806b3a completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abbabf7cdc81909636dff34badc1c5 completed March 7, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae58ca5bc88190abc61e3a6140f668 completed March 9, 2026, 5:21 a.m.
Created at: March 4, 2026, 7:43 p.m.