Triple

T6315737
Position Surface form Disambiguated ID Type / Status
Subject Robert Taft Jr. E141609 entity
Predicate mother P120 FINISHED
Object Martha Wheaton Bowers E348214 NE FINISHED

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: Martha Wheaton Bowers | Statement: [Robert Taft Jr., mother, Martha Wheaton Bowers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martha Wheaton Bowers
Context triple: [Robert Taft Jr., mother, Martha Wheaton Bowers]
  • A. Martha Wheaton Bowers chosen
    Martha Wheaton Bowers was the wife of prominent U.S. Senator Robert A. Taft and a member of a politically influential American family.
  • B. Martha Hunt
    Martha Hunt is an American fashion model best known for her work with Victoria’s Secret, including serving as a Victoria’s Secret Angel.
  • C. Maria Bissell Hotchkiss
    Maria Bissell Hotchkiss was an American philanthropist best known for endowing and establishing the prestigious Hotchkiss School in Lakeville, Connecticut.
  • D. Elizabeth Griscom
    Elizabeth Griscom, better known as Betsy Ross, was an American upholsterer and seamstress traditionally credited with sewing the first flag of the United States.
  • E. Annie M. Boughton
    Annie M. Boughton was the wife of American politician and first U.S. Secretary of Commerce William C. Redfield.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c008d13b8c8190be47d896eb735605 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c064a34e6081909b91984a3e815176 completed March 22, 2026, 9:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69c67c3b6cdc8190ad9e10957e301a57 completed March 27, 2026, 12:46 p.m.
Created at: March 22, 2026, 4:28 p.m.