Triple

T23365587
Position Surface form Disambiguated ID Type / Status
Subject Newtown, Johannesburg E593309 entity
Predicate near P350 FINISHED
Object Fordsburg 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: Fordsburg | Statement: [Newtown, Johannesburg, near, Fordsburg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fordsburg
Context triple: [Newtown, Johannesburg, near, Fordsburg]
  • A. Fordsburg chosen
    Fordsburg is a historic, culturally diverse suburb of Johannesburg known for its strong Indian and Muslim community, bustling markets, and vibrant street life.
  • B. Temperanceville
    Temperanceville is a small community within the Township of King in Ontario, Canada, known for its rural character and historic roots.
  • C. Oreston
    Oreston is a suburban district of Plymouth in Devon, England, known for its riverside location and maritime character.
  • D. Slaughterville
    Slaughterville is a small rural town in central Oklahoma, United States, known for its agricultural character and proximity to the city of Norman.
  • E. Rossville
    Rossville is a small rural locality in Far North Queensland, Australia, situated within the Shire of Cook and known for its rainforest surroundings and proximity to the Bloomfield Track.
  • 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_69e25d2593c88190bcdf4a716a94ccb2 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a0ab7fc481908b496ec9b543eddd completed April 29, 2026, 6:09 a.m.
Created at: April 17, 2026, 5:31 p.m.