Triple

T6087213
Position Surface form Disambiguated ID Type / Status
Subject Sasolburg E135668 entity
Predicate locatedIn P40 FINISHED
Object Vaal Triangle E54119 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: Vaal Triangle | Statement: [Sasolburg, locatedIn, Vaal Triangle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vaal Triangle
Context triple: [Sasolburg, locatedIn, Vaal Triangle]
  • A. Vaal Triangle chosen
    The Vaal Triangle is a major industrial and urban region in South Africa, centered around the Vaal River and known for its heavy manufacturing and petrochemical industries.
  • B. Mata Khivi
    Mata Khivi was a revered Sikh figure known for her service, compassion, and role in developing the tradition of the Guru ka Langar (community kitchen).
  • C. Kraaifontein
    Kraaifontein is a residential suburb in the northern outskirts of Cape Town, South Africa, known for its mixed urban and semi-rural character.
  • D. Sabie
    Sabie is a small forestry and tourism town in northeastern South Africa, known as a gateway to waterfalls and scenic routes near the Drakensberg escarpment.
  • E. Juta Valley
    Juta Valley is a scenic alpine valley in the Greater Caucasus of northeastern Georgia, popular for hiking, trekking, and mountain tourism near the village of Juta.
  • 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.