Triple

T20429579
Position Surface form Disambiguated ID Type / Status
Subject Margaret Sherman E501093 entity
Predicate name P16 FINISHED
Object Margaret Sherman 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: Margaret Sherman | Statement: [Margaret Sherman, name, Margaret Sherman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Margaret Sherman
Context triple: [Margaret Sherman, name, Margaret Sherman]
  • A. Margaret Sherman chosen
    Margaret Sherman was the wife of prominent American architect and urban planner Daniel Burnham, known for her role within Chicago’s elite social circles during the late 19th and early 20th centuries.
  • B. Martha Sherman
    Martha Sherman was the wife of Jeremiah Day, the long-serving president of Yale College in the early 19th century.
  • C. Margaret Shepard
    Margaret Shepard was a member of the prominent Vanderbilt family, known as the daughter of Margaret Louisa Vanderbilt Shepard and part of the influential American Gilded Age elite.
  • D. Marjorie Bach
    Marjorie Bach is an American woman known for her marriage to Eagles guitarist Joe Walsh and as the sister of actress and model Barbara Bach.
  • E. Margaret Heidenry
    Margaret Heidenry is a screenwriter best known for her work on the animated Disney sequel "Cinderella III: A Twist in Time."
  • 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_69e0b4aa68fc8190b1a14c55575ef04a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67bac39288190b294b291301ac843 completed April 20, 2026, 7:17 p.m.
Created at: April 16, 2026, 11:31 a.m.