Triple

T38021825
Position Surface form Disambiguated ID Type / Status
Subject Mandla Dlamini E948655 entity
Predicate hasSurnameOriginRegion P179683 FINISHED
Object Southern Africa 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: Southern Africa | Statement: [Mandla Dlamini, hasSurnameOriginRegion, Southern Africa]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasSurnameOriginRegion
Context triple: [Mandla Dlamini, hasSurnameOriginRegion, Southern Africa]
  • A. hasSurnameRegionAssociation
    Indicates that there is a relationship between a surname and a geographic region, such as origin, prevalence, or cultural association.
  • B. surnameLikelyOriginRegion chosen
    Indicates the geographic region from which a person’s surname is most likely to have originated.
  • C. hasNameOrigin
    Indicates that the origin or source of an entity’s name is specified by the related entity.
  • D. hasSurnameEthymology
    Indicates that an entity’s surname originates from, or is derived based on, a specified source, language, or etymological root.
  • E. familyNameOriginType
    Indicates the type or source of origin associated with a person's family name.
  • F. None of above.

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_69f76efc10448190aff5fb566b98f952 completed May 3, 2026, 3:51 p.m.
NER Named-entity recognition batch_6a0076c0a5c4819088b17b95511b93ed completed May 10, 2026, 12:14 p.m.
PD Predicate disambiguation batch_6a007638a67c81909c091335142260ab completed May 10, 2026, 12:12 p.m.
Created at: May 3, 2026, 4:20 p.m.