Triple

T14037704
Position Surface form Disambiguated ID Type / Status
Subject Southwest Bantu E337755 entity
Predicate hasMemberLanguage P7390 FINISHED
Object Umbundu language E532704 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: Umbundu language | Statement: [Southwest Bantu, hasMemberLanguage, Umbundu language]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Umbundu language
Context triple: [Southwest Bantu, hasMemberLanguage, Umbundu language]
  • A. Umbundu language chosen
    The Umbundu language is a major Bantu language spoken primarily by the Ovimbundu people in central and southern Angola.
  • B. Mbunda language
    The Mbunda language is a Bantu language spoken primarily by the Mbunda people in parts of Angola and Zambia.
  • C. Lunda language
    The Lunda language is a Bantu language spoken primarily in parts of Angola, the Democratic Republic of the Congo, and Zambia by the Lunda people.
  • D. Tontemboan language
    The Tontemboan language is an Austronesian language spoken by the Tontemboan people of North Sulawesi, Indonesia, and is one of the traditional Minahasan languages of the region.
  • E. Gbaya-Mbodomo language
    The Gbaya-Mbodomo language is a Niger-Congo language spoken by the Gbaya people of Central Africa, particularly in parts of the Central African Republic and neighboring regions.
  • 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_69d81c664e48819088cbd8f433aeffe5 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de30e312148190a6be0a3258364e6e completed April 14, 2026, 12:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbc33bc20081909abea7e64d1bd578 completed May 6, 2026, 10:39 p.m.
Created at: April 9, 2026, 10:20 p.m.