Triple

T16591310
Position Surface form Disambiguated ID Type / Status
Subject Braamfontein Spruit E403091 entity
Predicate partOf P40 FINISHED
Object Johannesburg green infrastructure network
The Johannesburg green infrastructure network is an interconnected system of rivers, parks, open spaces, and ecological corridors across Johannesburg designed to support biodiversity, recreation, and climate resilience.
E1222209 NE FINISHED

How this triple was built (4 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: Johannesburg green infrastructure network | Statement: [Braamfontein Spruit, partOf, Johannesburg green infrastructure network]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Johannesburg green infrastructure network
Context triple: [Braamfontein Spruit, partOf, Johannesburg green infrastructure network]
  • A. Barcelona metropolitan green infrastructure network
    The Barcelona metropolitan green infrastructure network is a coordinated system of natural and semi-natural spaces, corridors, and ecosystems designed to enhance biodiversity, climate resilience, and quality of life across the Barcelona metropolitan area.
  • B. City of Bristol green infrastructure network
    The City of Bristol green infrastructure network is a coordinated system of parks, natural areas, and green corridors across Bristol designed to support biodiversity, recreation, and climate resilience.
  • C. Busan urban green network
    The Busan urban green network is a planned system of interconnected parks, greenways, and ecological corridors designed to enhance environmental quality and recreational space across the city of Busan, South Korea.
  • D. Birmingham metropolitan area green space network
    The Birmingham metropolitan area green space network is a connected system of parks, nature preserves, and recreational greenways that provides ecological conservation, outdoor recreation, and scenic natural areas throughout the greater Birmingham region.
  • E. Knoxville urban wilderness network
    The Knoxville urban wilderness network is a connected system of parks, trails, and natural areas in and around Knoxville, Tennessee, designed to provide extensive outdoor recreation and conservation spaces within an urban setting.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Johannesburg green infrastructure network
Triple: [Braamfontein Spruit, partOf, Johannesburg green infrastructure network]
Generated description
The Johannesburg green infrastructure network is an interconnected system of rivers, parks, open spaces, and ecological corridors across Johannesburg designed to support biodiversity, recreation, and climate resilience.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Johannesburg green infrastructure network
Target entity description: The Johannesburg green infrastructure network is an interconnected system of rivers, parks, open spaces, and ecological corridors across Johannesburg designed to support biodiversity, recreation, and climate resilience.
  • A. Barcelona metropolitan green infrastructure network
    The Barcelona metropolitan green infrastructure network is a coordinated system of natural and semi-natural spaces, corridors, and ecosystems designed to enhance biodiversity, climate resilience, and quality of life across the Barcelona metropolitan area.
  • B. City of Bristol green infrastructure network
    The City of Bristol green infrastructure network is a coordinated system of parks, natural areas, and green corridors across Bristol designed to support biodiversity, recreation, and climate resilience.
  • C. Busan urban green network
    The Busan urban green network is a planned system of interconnected parks, greenways, and ecological corridors designed to enhance environmental quality and recreational space across the city of Busan, South Korea.
  • D. Birmingham metropolitan area green space network
    The Birmingham metropolitan area green space network is a connected system of parks, nature preserves, and recreational greenways that provides ecological conservation, outdoor recreation, and scenic natural areas throughout the greater Birmingham region.
  • E. Knoxville urban wilderness network
    The Knoxville urban wilderness network is a connected system of parks, trails, and natural areas in and around Knoxville, Tennessee, designed to provide extensive outdoor recreation and conservation spaces within an urban setting.
  • F. None of above. chosen

Provenance (5 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_69d88387363c8190a97a0c942130de97 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e359a012e081909a0604dde3c04bbb completed April 18, 2026, 10:14 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00759b9e5081909815d2cd00d44490 completed May 10, 2026, 12:10 p.m.
NEDg Description generation batch_6a007680bc7c81908c81ad690035ed47 completed May 10, 2026, 12:13 p.m.
NED2 Entity disambiguation (via description) batch_6a007734abd481909c9c698f2aef7632 completed May 10, 2026, 12:16 p.m.
Created at: April 10, 2026, 5:16 a.m.