Triple

T17493750
Position Surface form Disambiguated ID Type / Status
Subject Peniston Lamb (MP) E425996 entity
Predicate residence P75 FINISHED
Object Melbourne House, London 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: Melbourne House, London | Statement: [Peniston Lamb (MP), residence, Melbourne House, London]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Melbourne House, London
Context triple: [Peniston Lamb (MP), residence, Melbourne House, London]
  • A. Melbourne House chosen
    Melbourne House was a prominent London townhouse associated with British high society and political life in the late 18th and early 19th centuries.
  • B. Melbourne House
    Melbourne House was a British video game publisher and developer best known for its influential 1980s home computer titles and licensed adaptations.
  • C. Bloomsbury
    Bloomsbury is a British independent publishing house best known for releasing the Harry Potter series and a wide range of literary and academic works.
  • D. Bloomsbury
    Bloomsbury is a central London district renowned for its literary heritage, academic institutions, and garden squares.
  • E. Camden House
    Camden House is a teaching and administrative building that forms part of the University College Birmingham city-centre campus.
  • 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_69d889dccf7481909264a1844a2e9100 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e451d782688190afb76fa080867315 completed April 19, 2026, 3:53 a.m.
Created at: April 10, 2026, 5:48 a.m.