Triple

T14764048
Position Surface form Disambiguated ID Type / Status
Subject Michael Gerald Ford E346945 entity
Predicate relative P37 FINISHED
Object William Warren
William Warren is a relative of Michael Gerald Ford, the son of former U.S. President Gerald Ford.
E1284614 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: William Warren | Statement: [Michael Gerald Ford, relative, William Warren]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Warren
Context triple: [Michael Gerald Ford, relative, William Warren]
  • A. James Warren Sever
    James Warren Sever was a Harvard University alumnus and benefactor after whom the historic Sever Hall in Harvard Yard is named.
  • B. William Allyn
    William Allyn is a film and television producer best known for his work on the 1987 comedy "Rich and Famous."
  • C. Samuel Cutler Ward
    Samuel Cutler Ward was a 19th-century American lobbyist, bon vivant, and socialite known for his influential connections in politics and high society.
  • D. Warren Wells
    Warren Wells was an American professional football wide receiver best known for his standout seasons with the Oakland Raiders in the late 1960s.
  • E. Samuel A. Ward
    Samuel A. Ward was an American organist and composer best known for writing the melody later used for the patriotic song "America the Beautiful."
  • 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: William Warren
Triple: [Michael Gerald Ford, relative, William Warren]
Generated description
William Warren is a relative of Michael Gerald Ford, the son of former U.S. President Gerald Ford.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: William Warren
Target entity description: William Warren is a relative of Michael Gerald Ford, the son of former U.S. President Gerald Ford.
  • A. James Warren Sever
    James Warren Sever was a Harvard University alumnus and benefactor after whom the historic Sever Hall in Harvard Yard is named.
  • B. William Allyn
    William Allyn is a film and television producer best known for his work on the 1987 comedy "Rich and Famous."
  • C. Samuel Cutler Ward
    Samuel Cutler Ward was a 19th-century American lobbyist, bon vivant, and socialite known for his influential connections in politics and high society.
  • D. Warren Wells
    Warren Wells was an American professional football wide receiver best known for his standout seasons with the Oakland Raiders in the late 1960s.
  • E. Samuel A. Ward
    Samuel A. Ward was an American organist and composer best known for writing the melody later used for the patriotic song "America the Beautiful."
  • 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_69d822e8896c819091169882f9b20486 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7f3a1608190b1b17624003a0c7f completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_6a023005e760819081b723a7246c78ce completed May 11, 2026, 7:37 p.m.
NEDg Description generation batch_6a023121d7b88190bd832d41f47c3fdd completed May 11, 2026, 7:42 p.m.
NED2 Entity disambiguation (via description) batch_6a02357111388190a0c7bc7ae7ca1a1b completed May 11, 2026, 8 p.m.
Created at: April 10, 2026, 1:30 a.m.