Triple

T6446478
Position Surface form Disambiguated ID Type / Status
Subject Tonga (Zimbabwe) E138354 entity
Predicate neighboringLanguages P16383 FINISHED
Object Lozi E50731 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: Lozi | Statement: [Tonga (Zimbabwe), neighboringLanguages, Lozi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lozi
Context triple: [Tonga (Zimbabwe), neighboringLanguages, Lozi]
  • A. Lozi chosen
    Lozi is a Bantu language spoken primarily by the Lozi people in western Zambia and surrounding regions of southern Africa.
  • B. Inibaloi
    Inibaloi is an Austronesian language spoken by the Ibaloi people of the northern Philippines, particularly in Benguet province on Luzon.
  • C. Chenu
    Chenu is a commune in northwestern France, located in the Sarthe department of the Pays de la Loire region.
  • D. Luba
    Luba is a coastal town and important port on the southern part of Bioko Island in Equatorial Guinea.
  • E. Luba
    The Luba are a major Bantu-speaking ethnic group of Central Africa, historically known for the powerful Luba Kingdom centered in what is now the Democratic Republic of the Congo.
  • 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_69c008aa61ac8190bc96715ed79fe2d8 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0698edeac81909426902471d8a57b completed March 22, 2026, 10:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69c64bcd09e0819097eb60d13e8058dd completed March 27, 2026, 9:20 a.m.
Created at: March 22, 2026, 4:46 p.m.