Triple

T23075459
Position Surface form Disambiguated ID Type / Status
Subject George Sarton E575317 entity
Predicate influenced P9 FINISHED
Object Lynn Thorndike 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: Lynn Thorndike | Statement: [George Sarton, influenced, Lynn Thorndike]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lynn Thorndike
Context triple: [George Sarton, influenced, Lynn Thorndike]
  • A. Lynn Thorndike chosen
    Lynn Thorndike was an influential American historian of medieval science and magic, best known for his monumental multi-volume work "A History of Magic and Experimental Science."
  • B. Helen Chandler
    Helen Chandler was an American stage and film actress best known for her portrayal of Mina Seward in the 1931 horror classic "Dracula."
  • C. Patricia Ann Ladd
    Patricia Ann Ladd is best known as the wife of influential American film producer and studio executive Alan Ladd Jr.
  • D. Ruth Hussey
    Ruth Hussey was an American actress best known for her sharp-witted supporting roles in classic Hollywood films of the 1930s and 1940s, including her Oscar-nominated performance in "The Philadelphia Story."
  • E. Constance Bennett
    Constance Bennett was a prominent American film actress of the 1920s and 1930s, known for her sophisticated screen presence and roles in early Hollywood talkies.
  • 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_69e245be28d48190ad1348d5a73db37d completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18c62c200819099c92654493288ad completed April 29, 2026, 4:43 a.m.
Created at: April 17, 2026, 3:56 p.m.