Triple

T21469703
Position Surface form Disambiguated ID Type / Status
Subject Lord Vernon E529692 entity
Predicate seat P75 FINISHED
Object Sudbury Hall NE NERFINISHED

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: Sudbury Hall | Statement: [Lord Vernon, seat, Sudbury Hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sudbury Hall
Context triple: [Lord Vernon, seat, Sudbury Hall]
  • A. Sudbury Hall chosen
    Sudbury Hall is a historic country house in England renowned for its 17th-century architecture and as a filming location for period dramas.
  • B. Norton Hall
    Norton Hall is a building located on the North Campus that serves as one of its key facilities for academic and student activities.
  • C. Tatham Hall
    Tatham Hall is a student residence building located on the Keele Campus of York University in Toronto, Canada.
  • D. Saffron Hall
    Saffron Hall is a modern, high-quality performance venue in Saffron Walden, England, known for hosting leading orchestras, ensembles, and a wide range of classical and contemporary music events.
  • E. Sandon Hall
    Sandon Hall is a historic English country house and estate in Staffordshire, long associated with the Ryder family and the Earls of Harrowby.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c459acb481909bb6ee452a0045c7 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea12d9048190bf51ca3efc435a64 completed April 23, 2026, 9:44 a.m.
Created at: April 16, 2026, 6:16 p.m.