Triple

T12405982
Position Surface form Disambiguated ID Type / Status
Subject Dedworth E296386 entity
Predicate hasPark P105 FINISHED
Object Dedworth Manor Park
Dedworth Manor Park is a local public green space in the Dedworth area, offering recreational facilities and open parkland for community use.
 E981864 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: Dedworth Manor Park | Statement: [Dedworth, hasPark, Dedworth Manor Park]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dedworth Manor Park
Context triple: [Dedworth, hasPark, Dedworth Manor Park]
  • A. Windlestone Park
    Windlestone Park is the historic landscaped parkland and grounds surrounding Windlestone Hall in County Durham, England.
  • B. Manor Park
    Manor Park is a public green space in Aldershot, Hampshire, known for its open lawns, recreational facilities, and community events.
  • C. Manor Park
    Manor Park is a residential neighbourhood of the town of Knutsford in Cheshire, England.
  • D. Manor Park
    Manor Park is a residential district in East London known for its diverse community and proximity to major transport links into central London.
  • E. Manor Park
    Manor Park is a public green space in the London Borough of Sutton, offering recreational areas and natural surroundings for local residents.
  • 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: Dedworth Manor Park
Triple: [Dedworth, hasPark, Dedworth Manor Park]
Generated description
Dedworth Manor Park is a local public green space in the Dedworth area, offering recreational facilities and open parkland for community use.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dedworth Manor Park
Target entity description: Dedworth Manor Park is a local public green space in the Dedworth area, offering recreational facilities and open parkland for community use.
  • A. Windlestone Park
    Windlestone Park is the historic landscaped parkland and grounds surrounding Windlestone Hall in County Durham, England.
  • B. Manor Park
    Manor Park is a public park in Glossop, Derbyshire, known for its landscaped gardens, recreational facilities, and scenic views of the surrounding countryside.
  • C. Manor Park
    Manor Park is a residential neighbourhood of the town of Knutsford in Cheshire, England.
  • D. Manor Park
    Manor Park is a residential neighbourhood in Ottawa, Ontario, known for its tree-lined streets, parks, and proximity to the affluent Rockcliffe Park area.
  • E. Manor Park
    Manor Park is a residential district in East London known for its diverse community and proximity to major transport links into central London.
  • 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_69d6ad9f464c81909db36d7e96e34b9e completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d48f1908190918551c794f98fe3 completed April 10, 2026, 7:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63486d1b881908d94218d2c391123 completed May 2, 2026, 5:29 p.m.
NEDg Description generation batch_69f637575a9c8190b677b59e9739af49 completed May 2, 2026, 5:41 p.m.
NED2 Entity disambiguation (via description) batch_69f6380223d08190959e524ad146d0e0 completed May 2, 2026, 5:44 p.m.
Created at: April 8, 2026, 9:55 p.m.