Triple

T20002127
Position Surface form Disambiguated ID Type / Status
Subject Maxwell Perkins E494357 entity
Predicate spouse P13 FINISHED
Object Louise Saunders 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: Louise Saunders | Statement: [Maxwell Perkins, spouse, Louise Saunders]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Louise Saunders
Context triple: [Maxwell Perkins, spouse, Louise Saunders]
  • A. Louise Saunders chosen
    Louise Saunders was an American writer and playwright best known for her marriage to influential editor Maxwell Perkins and for authoring children’s literature and stage works in the early 20th century.
  • B. Louise Thomas
    Louise Thomas was the wife of pioneering British aviation designer and test pilot Geoffrey de Havilland.
  • C. Louise Wilson
    Louise Wilson is known primarily as the daughter of American businessman and Xerox Corporation founder Joseph C. Wilson.
  • D. Louise Franklin
    Louise Franklin was the wife of British actor George Coulouris, known primarily in relation to his personal life.
  • E. Louise Boyd
    Louise Boyd was an American Arctic explorer, photographer, and philanthropist known for leading several expeditions to Greenland in the early 20th century.
  • 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_69da626b2d748190886981ea90c8b2ea completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e661a2e34481908a495cc5d077c41f completed April 20, 2026, 5:25 p.m.
Created at: April 11, 2026, 3:32 p.m.