Triple

T3827031
Position Surface form Disambiguated ID Type / Status
Subject Broket Hall E88713 entity
Predicate hasGrounds P7001 FINISHED
Object Brocket Park E494330 NE FINISHED

How this triple was built (2 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: Brocket Park | Statement: [Broket Hall, hasGrounds, Brocket Park]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brocket Park
Context triple: [Broket Hall, hasGrounds, Brocket Park]
  • A. Brocket Park chosen
    Brocket Park is a historic English country estate in Hertfordshire, best known for its grand stately home, landscaped grounds, and golf courses.
  • B. Browne Park
    Browne Park is a prominent rugby league stadium in Rockhampton, Queensland, known for hosting local and regional sporting events.
  • C. Bushy Park
    Bushy Park is a large historic royal park in southwest London that notably served as a key Allied military headquarters during World War II.
  • D. Shute Park
    Shute Park is a public park in Hillsboro, Oregon, known for its large green spaces, recreational facilities, and community events.
  • E. Tarrywile Park
    Tarrywile Park is a large public park and nature preserve in Danbury, Connecticut, known for its extensive hiking trails, scenic landscapes, and historic estate buildings.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69aed9538cf881909d9ce8ca4ac7c18c completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeeb64c72c8190b5f3d376aa4ee933 completed March 9, 2026, 3:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69bec330d09c819085930d71b21acb7c completed March 21, 2026, 4:11 p.m.
Created at: March 9, 2026, 3:17 p.m.