Triple

T17959656
Position Surface form Disambiguated ID Type / Status
Subject Schweizer-Reneke E449043 entity
Predicate hasNearbyCity P350 FINISHED
Object Bloemhof 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: Bloemhof | Statement: [Schweizer-Reneke, hasNearbyCity, Bloemhof]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bloemhof
Context triple: [Schweizer-Reneke, hasNearbyCity, Bloemhof]
  • A. Bloemhof chosen
    Bloemhof is a small South African town in the North West province, situated on the Vaal River and known for agriculture and freshwater fishing tourism.
  • B. Constantia Kloof
    Constantia Kloof is a residential suburb in Roodepoort, Johannesburg, known for its hilly terrain, views, and proximity to major commercial and transport routes.
  • C. Boschendal
    Boschendal is a historic South African wine estate renowned for its well-preserved Cape Dutch architecture and scenic setting in the Cape Winelands.
  • D. Villa Welgelegen
    Villa Welgelegen is an 18th-century neoclassical country house in Haarlem, Netherlands, renowned for its grand architecture and historical role as a residence of prominent political figures.
  • E. Doornfontein
    Doornfontein is an inner-city suburb of Johannesburg, South Africa, known for its mix of historic buildings, industrial areas, and educational institutions.
  • 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4b130b7a081908542a3bc6dab5842 completed April 19, 2026, 10:40 a.m.
Created at: April 10, 2026, 10:22 a.m.