Triple

T19574771
Position Surface form Disambiguated ID Type / Status
Subject Mary Garfield E489824 entity
Predicate givenName P17 FINISHED
Object Mary
Mary Garfield was the wife of U.S. President James A. Garfield and served as First Lady of the United States in 1881.
 E1382949 NE FINISHED

How this triple was built (4 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: Mary | Statement: [Mary Garfield, givenName, Mary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mary
Context triple: [Mary Garfield, givenName, Mary]
  • A. Mary
    Mary is the middle name of Edith Tolkien, the wife of author J.R.R. Tolkien.
  • B. Mary
    Mary is the birth name of American actress, comedian, and writer Lily Tomlin, known for her groundbreaking work in television, film, and theater.
  • C. Mary
    Mary is the given name of the American stage and film actress Josephine Hull, known for her roles in classic mid-20th-century theater and cinema.
  • D. Mary
    Mary is a character in the "Tunnel community" setting, known as one of the individuals living within its underground society.
  • E. Mary
    Mary is the given first name of American actress, author, and radio host Marilu Henner.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mary
Triple: [Mary Garfield, givenName, Mary]
Generated description
Mary Garfield was the wife of U.S. President James A. Garfield and served as First Lady of the United States in 1881.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mary
Target entity description: Mary Garfield was the wife of U.S. President James A. Garfield and served as First Lady of the United States in 1881.
  • A. Mary
    Mary is the given name of Mary Scott Lord Dimmick Harrison, the second wife of U.S. President Benjamin Harrison and former First Lady of the United States.
  • B. Mary
    Mary is the given name of Mary Elizabeth Baird Bryan, an American figure known primarily in relation to her husband, politician William Jennings Bryan.
  • C. Mary
    Mary is the first name of Tipper Gore, the American social issues advocate and former Second Lady of the United States.
  • D. Mary
    Mary is the given first name of Margaret Truman, the daughter of U.S. President Harry S. Truman and a noted author and singer.
  • E. Mary
    Mary is the given name of Mary Lincoln Beckwith, a granddaughter of U.S. President Abraham Lincoln.
  • F. None of above. chosen

Provenance (5 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_69d8e8dd9374819098e36349b3211663 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e64023fe148190900c6887896c8ea0 completed April 20, 2026, 3:03 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0757825ddc81908c08b061a9ec0984 completed May 15, 2026, 5:27 p.m.
NEDg Description generation batch_6a07584e664c8190967deed2e79e356b completed May 15, 2026, 5:30 p.m.
NED2 Entity disambiguation (via description) batch_6a0758dc31bc8190858815dc24b04ac4 completed May 15, 2026, 5:33 p.m.
Created at: April 10, 2026, 1:42 p.m.