Triple

T6974209
Position Surface form Disambiguated ID Type / Status
Subject Sanlam Limited E161674 entity
Predicate hasSubsidiary P254 FINISHED
Object Sanlam Corporate E31812 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: Sanlam Corporate | Statement: [Sanlam Limited, hasSubsidiary, Sanlam Corporate]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sanlam Corporate
Context triple: [Sanlam Limited, hasSubsidiary, Sanlam Corporate]
  • A. Sanlam chosen
    Sanlam is a major South African financial services group offering insurance, investment, and wealth management solutions across multiple markets.
  • B. Nedbank
    Nedbank is one of South Africa’s major financial institutions, offering a wide range of banking and financial services to retail, business, and corporate clients.
  • C. Investec
    Investec is an international specialist banking and asset management group headquartered in South Africa and the United Kingdom.
  • D. JSE Limited
    JSE Limited is the Johannesburg-based stock exchange and the primary securities market for South Africa and much of the African continent.
  • E. Swiss Re
    Swiss Re is a leading global reinsurance company headquartered in Zurich, Switzerland, providing risk transfer and insurance solutions worldwide.
  • 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_69c68854a0d88190bc0bf82263f1afce completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6db3bda908190a10a91dc8d043ef1 completed March 27, 2026, 7:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69c794318fb08190a9a89570b2a6999b completed March 28, 2026, 8:41 a.m.
Created at: March 27, 2026, 2:30 p.m.