Triple

T2118120
Position Surface form Disambiguated ID Type / Status
Subject Kirundi E43853 entity
Predicate usedByEthnicGroup P4709 FINISHED
Object Barundi E36947 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: Barundi | Statement: [Kirundi, usedByEthnicGroup, Barundi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barundi
Context triple: [Kirundi, usedByEthnicGroup, Barundi]
  • A. Burundi chosen
    Burundi is a small, landlocked country in East Africa known for its hilly terrain, location along Lake Tanganyika, and ethnically diverse population.
  • B. Rwanda
    Rwanda is a landlocked East African nation known for its dramatic recovery from the 1994 genocide, rapid economic growth, and strong conservation efforts, particularly for mountain gorillas.
  • C. Bunia
    Bunia is a city in northeastern Democratic Republic of the Congo that has been a focal point of regional conflict and international peacekeeping efforts.
  • D. Butaro, Rwanda
    Butaro, Rwanda is a rural town in northern Rwanda known for its innovative, community-focused health facilities and scenic volcanic landscapes.
  • E. Nzera
    Nzera is a settlement located within Tanzania’s Geita Region in East Africa.
  • 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_69a88717cfe48190b7ecdd68c824848a completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abbb3117c081908c5e748a869d1f9f completed March 7, 2026, 5:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69b2e7fbc76c8190a66110203d53f055 completed March 12, 2026, 4:21 p.m.
Created at: March 4, 2026, 7:44 p.m.