Triple

T19387892
Position Surface form Disambiguated ID Type / Status
Subject Lucy Ware Webb Hayes E484981 entity
Predicate child P120 FINISHED
Object Fanny Hayes 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: Fanny Hayes | Statement: [Lucy Ware Webb Hayes, child, Fanny Hayes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fanny Hayes
Context triple: [Lucy Ware Webb Hayes, child, Fanny Hayes]
  • A. Fanny Hayes chosen
    Fanny Hayes was the daughter of U.S. President Rutherford B. Hayes and First Lady Lucy Webb Hayes, who grew up in the White House during her father's administration.
  • B. Fanny Hayes
    Fanny Hayes was the mother of pioneering African American lyric tenor and composer Roland Hayes, who became one of the first internationally acclaimed Black concert artists.
  • C. Faye Medwick
    Faye Medwick is a fictional character appearing in the work titled "Chapter Two."
  • D. Faye Miller
    Faye Miller is a market research psychologist who becomes one of Don Draper’s significant romantic partners in the television series "Mad Men."
  • E. Faye Ward
    Faye Ward is a British film and television producer known for her work on acclaimed projects such as the historical drama "Suffragette."
  • 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_69d8e8d460d88190abf0591c5c9d2b0c completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e61b418f148190972b7b46038bc744 completed April 20, 2026, 12:25 p.m.
Created at: April 10, 2026, 1:36 p.m.