Triple

T22273683
Position Surface form Disambiguated ID Type / Status
Subject Mzilikazi E550545 entity
Predicate clan P1915 FINISHED
Object Khumalo 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: Khumalo | Statement: [Mzilikazi, clan, Khumalo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Khumalo
Context triple: [Mzilikazi, clan, Khumalo]
  • A. Khumalo chosen
    Khumalo is a common Southern African surname associated with notable figures in arts, politics, and public life, particularly in South Africa and Zimbabwe.
  • B. Khalatse
    Khalatse is a village in the Leh district of Ladakh, India, known as a historic stop on the old Silk Route along the Indus River.
  • C. Senzangakhona
    Senzangakhona was a Zulu chief best known as the father of Shaka Zulu, the famed 19th-century Zulu king and military leader.
  • D. Mokoena
    Mokoena is a common Southern African surname of Sotho-Tswana origin borne by various notable figures in politics, sports, and the arts.
  • E. Thokozani
    Thokozani is a given name most notably borne by Zimbabwean politician Thokozani Khupe.
  • 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_69e11e43d8208190aff4f9cf7f2c2a8a completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f14ea547e4819098baf88f3c605242 completed April 29, 2026, 12:19 a.m.
Created at: April 16, 2026, 8:40 p.m.