Triple

T6087233
Position Surface form Disambiguated ID Type / Status
Subject Sasolburg E135668 entity
Predicate hasIndustrialArea P40 FINISHED
Object Sasolburg Industrial Area E135668 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: Sasolburg Industrial Area | Statement: [Sasolburg, hasIndustrialArea, Sasolburg Industrial Area]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sasolburg Industrial Area
Context triple: [Sasolburg, hasIndustrialArea, Sasolburg Industrial Area]
  • A. Sasolburg chosen
    Sasolburg is an industrial town in South Africa’s Free State province, known primarily for its large petrochemical complex and proximity to the Vaal River.
  • B. Rai Industrial Estate
    Rai Industrial Estate is a major industrial hub in Haryana, India, hosting a wide range of manufacturing and commercial units.
  • C. Bothasig
    Bothasig is a residential suburb in the northern part of Cape Town, South Africa.
  • D. Highveld Techno Park
    Highveld Techno Park is a prominent business and technology hub in Centurion, South Africa, hosting numerous corporate offices and tech-oriented companies.
  • E. Loftus Versfeld Park
    Loftus Versfeld Park was the earlier name of the historic rugby and football stadium in Pretoria, South Africa, now known as Loftus Versfeld Stadium.
  • 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_69c0087bcc788190b20f093d3a6c60ec completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c0578bf2508190859c2dbd4c10b316 completed March 22, 2026, 8:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69c11d60e824819098a9f5fc5cc00be4 completed March 23, 2026, 11 a.m.
Created at: March 22, 2026, 4:12 p.m.