Triple

T20030576
Position Surface form Disambiguated ID Type / Status
Subject Canning River Regional Park E495109 entity
Predicate partOf P40 FINISHED
Object Perth metropolitan regional open space network
The Perth metropolitan regional open space network is a coordinated system of parks, reserves, and natural areas across the Perth region designed to protect environmental values and provide recreational green space for the community.
E1407886 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: Perth metropolitan regional open space network | Statement: [Canning River Regional Park, partOf, Perth metropolitan regional open space network]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Perth metropolitan regional open space network
Context triple: [Canning River Regional Park, partOf, Perth metropolitan regional open space network]
  • A. Wellington urban open space network
    The Wellington urban open space network is a connected system of parks, reserves, and green corridors across Wellington that provides recreation, ecological protection, and scenic landscapes for the city.
  • B. Melbourne green corridor network
    The Melbourne green corridor network is an interconnected system of waterways, parklands, and vegetated pathways that supports urban biodiversity, recreation, and ecological connectivity across the Melbourne metropolitan area.
  • C. Launceston parks and reserves network
    The Launceston parks and reserves network is a collection of public green spaces and natural reserves in and around Launceston, Tasmania, managed to provide recreation, conservation, and scenic attractions for residents and visitors.
  • 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. Western Sydney Parklands
    Western Sydney Parklands is a vast urban parkland corridor in Western Sydney that conserves significant remnants of the Cumberland Plain’s natural landscapes while providing extensive recreational spaces for the public.
  • 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: Perth metropolitan regional open space network
Triple: [Canning River Regional Park, partOf, Perth metropolitan regional open space network]
Generated description
The Perth metropolitan regional open space network is a coordinated system of parks, reserves, and natural areas across the Perth region designed to protect environmental values and provide recreational green space for the community.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Perth metropolitan regional open space network
Target entity description: The Perth metropolitan regional open space network is a coordinated system of parks, reserves, and natural areas across the Perth region designed to protect environmental values and provide recreational green space for the community.
  • A. Wellington urban open space network
    The Wellington urban open space network is a connected system of parks, reserves, and green corridors across Wellington that provides recreation, ecological protection, and scenic landscapes for the city.
  • B. Melbourne green corridor network
    The Melbourne green corridor network is an interconnected system of waterways, parklands, and vegetated pathways that supports urban biodiversity, recreation, and ecological connectivity across the Melbourne metropolitan area.
  • C. Launceston parks and reserves network
    The Launceston parks and reserves network is a collection of public green spaces and natural reserves in and around Launceston, Tasmania, managed to provide recreation, conservation, and scenic attractions for residents and visitors.
  • 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. Western Sydney Parklands
    Western Sydney Parklands is a vast urban parkland corridor in Western Sydney that conserves significant remnants of the Cumberland Plain’s natural landscapes while providing extensive recreational spaces for the public.
  • 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_69da626bfd288190aa5d65098b6433ae completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66291a00c8190b0b895909f32d623 completed April 20, 2026, 5:29 p.m.
NED1 Entity disambiguation (via context triple) batch_6a080e332c1c8190b72a813d8f078b33 completed May 16, 2026, 6:26 a.m.
NEDg Description generation batch_6a080fdd67ac8190ae6e23cab4a5b89e completed May 16, 2026, 6:34 a.m.
NED2 Entity disambiguation (via description) batch_6a0810a84da081908d5e662dccf38208 completed May 16, 2026, 6:37 a.m.
Created at: April 11, 2026, 3:36 p.m.