Triple

T3140021
Position Surface form Disambiguated ID Type / Status
Subject Kinyarwanda E65621 entity
Predicate closelyRelatedTo P37 FINISHED
Object Kirundi E43853 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: Kirundi | Statement: [Kinyarwanda, closelyRelatedTo, Kirundi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kirundi
Context triple: [Kinyarwanda, closelyRelatedTo, Kirundi]
  • A. Kirundi chosen
    Kirundi is a Bantu language primarily spoken in Burundi and neighboring regions of East Africa.
  • B. Kinyarwanda
    Kinyarwanda is a Bantu language spoken primarily in Rwanda, where it serves as a national and widely used lingua franca.
  • C. Kikongo
    Kikongo is a Bantu language widely spoken in Central Africa, particularly in the western regions of the Democratic Republic of the Congo and neighboring countries.
  • D. Kimbundu
    Kimbundu is a major Bantu language spoken primarily in northwestern Angola, especially around the capital Luanda, by the Ambundu people.
  • E. Lingala
    Lingala is a Bantu language widely spoken as a lingua franca in the Democratic Republic of the Congo and the Republic of the Congo, especially in urban centers and along the Congo River.
  • 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_69ad8582f564819088c27e1f96153938 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada57743e08190a1069c62e32f1bd4 completed March 8, 2026, 4:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69b235b2aa388190ae9dc569b951206d completed March 12, 2026, 3:40 a.m.
Created at: March 8, 2026, 3:05 p.m.