Triple

T17988987
Position Surface form Disambiguated ID Type / Status
Subject Oshikwanyama E430316 entity
Predicate closelyRelatedTo P37 FINISHED
Object Oshindonga 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: Oshindonga | Statement: [Oshikwanyama, closelyRelatedTo, Oshindonga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oshindonga
Context triple: [Oshikwanyama, closelyRelatedTo, Oshindonga]
  • A. Oshindonga chosen
    Oshindonga is a standardized Bantu language variety spoken primarily in northern Namibia and southern Angola, forming one of the main dialects of the Oshiwambo language cluster.
  • B. Oshikwambi
    Oshikwambi is a regional dialect of the Oshiwambo language spoken by the Kwambi people in northern Namibia.
  • C. Bongwe
    Bongwe is a dialect of the Duala language spoken by the Duala people of Cameroon.
  • D. Owendo
    Owendo is a port city in western Gabon that serves as an important industrial and maritime hub near the capital, Libreville.
  • E. Chindau
    Chindau is a Bantu language spoken primarily by the Ndau people in parts of Mozambique and Zimbabwe.
  • 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_69d8b90364248190a37381adea932f42 completed April 10, 2026, 8:46 a.m.
NER Named-entity recognition batch_69e4b29e47a88190be58b79c73d3e652 completed April 19, 2026, 10:46 a.m.
Created at: April 10, 2026, 10:23 a.m.