Triple

T20283408
Position Surface form Disambiguated ID Type / Status
Subject Christianna Brand E503208 entity
Predicate spouse P13 FINISHED
Object Roland Lewis 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: Roland Lewis | Statement: [Christianna Brand, spouse, Roland Lewis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roland Lewis
Context triple: [Christianna Brand, spouse, Roland Lewis]
  • A. Roland Lewis chosen
    Roland Lewis was the husband of British crime novelist and children's author Christianna Brand.
  • B. Roland Wilson
    Roland Wilson is a central character in the sitcom "The Golden Palace," known for his role in the ensemble that continues the story of the original "Golden Girls" cast.
  • C. Michael Waddell
    Michael Waddell is a sports executive best known for serving as president of the Orlando Apollos in the Alliance of American Football.
  • D. H. Gregg Lewis
    H. Gregg Lewis was an influential American labor economist known for his pioneering empirical work on labor supply, wage determination, and union effects on labor markets.
  • E. Douglas Peters
    Douglas Peters was a Canadian economist, banker, and Liberal politician who served as a Member of Parliament and Secretary of State for International Financial Institutions in the 1990s.
  • 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_69e0b4b0e79c8190bd61f22ef1329fa8 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6769049b48190bc449557b79b9e81 completed April 20, 2026, 6:55 p.m.
Created at: April 16, 2026, 10:48 a.m.