Triple

T23270993
Position Surface form Disambiguated ID Type / Status
Subject Ikalanga E588287 entity
Predicate hasAlternativeName P39 FINISHED
Object Kalanga 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: Kalanga | Statement: [Ikalanga, hasAlternativeName, Kalanga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kalanga
Context triple: [Ikalanga, hasAlternativeName, Kalanga]
  • A. Kalanga chosen
    Kalanga is a Southern Bantu language spoken primarily in southwestern Zimbabwe and northeastern Botswana by the Kalanga people.
  • B. Delanga
    Delanga is a town and administrative block in the Puri district of Odisha, India, known for its agrarian communities and proximity to major cultural and religious centers in the region.
  • C. Kinkala
    Kinkala is a town in the Republic of the Congo that serves as an administrative and economic center for the surrounding region.
  • D. Talanga
    Talanga is a town and municipality in central Honduras known for its agricultural activities and location along the highway connecting Tegucigalpa with the country's northern regions.
  • E. Loenga
    Loenga is a small residential and industrial neighborhood in Oslo, Norway, situated near the railway yards and the Oslofjord.
  • 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_69e25d148adc819088efbf42672604e9 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1957418fc819085ee528622e0c6de completed April 29, 2026, 5:21 a.m.
Created at: April 17, 2026, 4:45 p.m.