Triple

T21414575
Position Surface form Disambiguated ID Type / Status
Subject Anderlecht E528266 entity
Predicate hasMuseum P105 FINISHED
Object Erasmus House 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: Erasmus House | Statement: [Anderlecht, hasMuseum, Erasmus House]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Erasmus House
Context triple: [Anderlecht, hasMuseum, Erasmus House]
  • A. Erasmus House chosen
    Erasmus House is a historic museum in Anderlecht, Brussels, dedicated to the life and legacy of the Renaissance humanist Desiderius Erasmus.
  • B. Gresham House
    Gresham House is a historic London building that once served as the residence of Sir Thomas Gresham and later housed the Royal Exchange.
  • C. Kemp House
    Kemp House is a historic early 19th-century wooden mission house in Kerikeri, New Zealand, and one of the country’s oldest surviving European buildings.
  • D. Tuynhuys
    Tuynhuys is a historic Cape Dutch-style building in Cape Town that serves as the official office and ceremonial residence of South Africa’s head of state.
  • E. Caxton House
    Caxton House is a government office building located on Tothill Street in Westminster, central London.
  • 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_69e0c454c248819093425d1099101c09 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e8b2032fe48190907b282e2fffa2bd completed April 22, 2026, 11:33 a.m.
Created at: April 16, 2026, 5:45 p.m.