Triple

T15056876
Position Surface form Disambiguated ID Type / Status
Subject Arenberg Castle E379517 entity
Predicate hasPark P105 FINISHED
Object Arenberg Park
Arenberg Park is a historic public green space surrounding Arenberg Castle in Leuven, Belgium, known for its expansive lawns, tree-lined paths, and recreational areas.
E1167424 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: Arenberg Park | Statement: [Arenberg Castle, hasPark, Arenberg Park]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arenberg Park
Context triple: [Arenberg Castle, hasPark, Arenberg Park]
  • A. Hagen Park
    Hagen Park is a public recreational park located in the city of Wilton Manors, Florida.
  • B. Ghesquiere Park
    Ghesquiere Park is a public recreational park located in the suburban community of Grosse Pointe Woods, Michigan.
  • C. Hawthorne Park
    Hawthorne Park is a public recreational park located in the riverside suburb of Hawthorne in Brisbane, Queensland, Australia.
  • D. Harleman Park
    Harleman Park is a local public park in Cornelius, Oregon, offering outdoor recreational space for residents and visitors.
  • E. Shute Park
    Shute Park is a public park in Hillsboro, Oregon, known for its large green spaces, recreational facilities, and community events.
  • 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: Arenberg Park
Triple: [Arenberg Castle, hasPark, Arenberg Park]
Generated description
Arenberg Park is a historic public green space surrounding Arenberg Castle in Leuven, Belgium, known for its expansive lawns, tree-lined paths, and recreational areas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Arenberg Park
Target entity description: Arenberg Park is a historic public green space surrounding Arenberg Castle in Leuven, Belgium, known for its expansive lawns, tree-lined paths, and recreational areas.
  • A. Hagen Park
    Hagen Park is a public recreational park located in the city of Wilton Manors, Florida.
  • B. Ghesquiere Park
    Ghesquiere Park is a public recreational park located in the suburban community of Grosse Pointe Woods, Michigan.
  • C. Hawthorne Park
    Hawthorne Park is a public recreational park located in the riverside suburb of Hawthorne in Brisbane, Queensland, Australia.
  • D. Harleman Park
    Harleman Park is a local public park in Cornelius, Oregon, offering outdoor recreational space for residents and visitors.
  • E. Shute Park
    Shute Park is a public park in Hillsboro, Oregon, known for its large green spaces, recreational facilities, and community events.
  • 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_69d85cd64d108190853797a95c11cc45 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69deda937f788190899d81bbb2084443 completed April 15, 2026, 12:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f24967c8190b0bdb84b88a0aaa3 completed May 9, 2026, 4:21 p.m.
NEDg Description generation batch_69ff5fd7068881909a8d85f6bdccedfc completed May 9, 2026, 4:24 p.m.
NED2 Entity disambiguation (via description) batch_69ff6073193c8190bb9d1ab18d3d816c completed May 9, 2026, 4:27 p.m.
Created at: April 10, 2026, 3:01 a.m.