Triple

T19536784
Position Surface form Disambiguated ID Type / Status
Subject Lady Rose Gilman E488786 entity
Predicate spouse P13 FINISHED
Object George Gilman 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: George Gilman | Statement: [Lady Rose Gilman, spouse, George Gilman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Gilman
Context triple: [Lady Rose Gilman, spouse, George Gilman]
  • A. George Houghton Gilman chosen
    George Houghton Gilman was the second husband of American writer and feminist theorist Charlotte Perkins Gilman, with whom he shared a long and supportive partnership.
  • B. George Philip Wells
    George Philip Wells was a British zoologist and author, known both for his scientific work and as the son of writer H. G. Wells.
  • C. E. V. Cunningham
    E. V. Cunningham was the crime-fiction pen name of American novelist Howard Fast, under which he wrote a series of popular mystery and detective novels.
  • D. Philip Leslie Hale
    Philip Leslie Hale was an American Impressionist painter and influential art teacher associated with the Boston School, known for his luminous landscapes and figure paintings.
  • E. Thomas Mayne
    Thomas Mayne was an Australian food scientist best known for creating the chocolate malted milk drink Milo in the 1930s.
  • 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_69d8e8db5b6c8190984b61f91981f575 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6386f0fac819081bbc29172c8965e completed April 20, 2026, 2:30 p.m.
Created at: April 10, 2026, 1:41 p.m.