Triple

T18412773
Position Surface form Disambiguated ID Type / Status
Subject Paul Kruger Street, Pretoria E441803 entity
Predicate partOf P40 FINISHED
Object Pretoria CBD street network NE NERFINISHED

How this triple was built (3 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: Pretoria CBD street network | Statement: [Paul Kruger Street, Pretoria, partOf, Pretoria CBD street network]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pretoria CBD street network
Context triple: [Paul Kruger Street, Pretoria, partOf, Pretoria CBD street network]
  • A. Napier urban road network
    The Napier urban road network is the system of streets and arterial routes serving the city of Napier, New Zealand, connecting its Art Deco city centre with surrounding suburbs and regional highways.
  • B. Johannesburg metropolitan road network
    The Johannesburg metropolitan road network is an integrated system of urban freeways, motorways, and arterial roads that connects and serves the greater Johannesburg area in South Africa.
  • C. Recife urban road network
    The Recife urban road network is the interconnected system of streets, avenues, and highways that supports transportation and mobility throughout the city of Recife, Brazil.
  • D. City of London street network
    The City of London street network is the dense, historic web of roads and lanes at the core of London’s financial district, characterized by medieval street patterns interwoven with modern thoroughfares.
  • E. Cambridge city centre street network
    Cambridge city centre street network is the interconnected system of historic streets, lanes, and pedestrian routes that forms the core urban layout of central Cambridge, England.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pretoria CBD street network
Target entity description: The Pretoria CBD street network is the central grid of roads and intersections that structures traffic flow, access, and urban activity in downtown Pretoria, South Africa.
  • A. Napier urban road network
    The Napier urban road network is the system of streets and arterial routes serving the city of Napier, New Zealand, connecting its Art Deco city centre with surrounding suburbs and regional highways.
  • B. Johannesburg metropolitan road network
    The Johannesburg metropolitan road network is an integrated system of urban freeways, motorways, and arterial roads that connects and serves the greater Johannesburg area in South Africa.
  • C. Recife urban road network
    The Recife urban road network is the interconnected system of streets, avenues, and highways that supports transportation and mobility throughout the city of Recife, Brazil.
  • D. City of London street network
    The City of London street network is the dense, historic web of roads and lanes at the core of London’s financial district, characterized by medieval street patterns interwoven with modern thoroughfares.
  • E. Cambridge city centre street network
    Cambridge city centre street network is the interconnected system of historic streets, lanes, and pedestrian routes that forms the core urban layout of central Cambridge, England.
  • F. None of above. chosen

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_69d8b9eb8a508190a942fd75ebd8b1dc completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e51a259c1c819094e710bb4a7ace75 completed April 19, 2026, 6:08 p.m.
Created at: April 10, 2026, 10:47 a.m.