Triple

T9582155
Position Surface form Disambiguated ID Type / Status
Subject Daniel Mann E231197 entity
Predicate spouse P13 FINISHED
Object Mary Kathleen Williams
Mary Kathleen Williams is known primarily as the wife of American film and theater director Daniel Mann.
 E828894 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 Kathleen Williams | Statement: [Daniel Mann, spouse, Mary Kathleen Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mary Kathleen Williams
Context triple: [Daniel Mann, spouse, Mary Kathleen Williams]
  • A. Mary Cleary
    Mary Cleary was the wife of Commodore John Barry, an early U.S. naval officer often called the "Father of the American Navy."
  • B. Mary Kathleen Turner
    Mary Kathleen Turner is an American actress known for her distinctive husky voice and leading roles in 1980s films such as "Body Heat," "Romancing the Stone," and "Peggy Sue Got Married."
  • C. Catherine Anne Williams
    Catherine Anne Williams was the wife of 19th-century British politician and free-trade advocate Richard Cobden.
  • D. Marie Burke
    Marie Burke was a British actress and singer active in the early to mid-20th century, known for her work on stage, film, and radio.
  • E. Mary Durkan
    Mary Durkan is an Irish politician known for her involvement in local and national public affairs.
  • 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 Kathleen Williams
Triple: [Daniel Mann, spouse, Mary Kathleen Williams]
Generated description
Mary Kathleen Williams is known primarily as the wife of American film and theater director Daniel Mann.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mary Kathleen Williams
Target entity description: Mary Kathleen Williams is known primarily as the wife of American film and theater director Daniel Mann.
  • A. Mary Cleary
    Mary Cleary was the wife of Commodore John Barry, an early U.S. naval officer often called the "Father of the American Navy."
  • B. Mary Kathleen Turner
    Mary Kathleen Turner is an American actress known for her distinctive husky voice and leading roles in 1980s films such as "Body Heat," "Romancing the Stone," and "Peggy Sue Got Married."
  • C. Catherine Anne Williams
    Catherine Anne Williams was the wife of 19th-century British politician and free-trade advocate Richard Cobden.
  • D. Marie Burke
    Marie Burke was a British actress and singer active in the early to mid-20th century, known for her work on stage, film, and radio.
  • E. Mary Durkan
    Mary Durkan is an Irish politician known for her involvement in local and national public affairs.
  • 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_69ca848161688190a68d514a0a9d5129 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd99cd59008190888eb11f00f61994 completed April 1, 2026, 10:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69d20cbe7fb88190a945870540d4c973 completed April 5, 2026, 7:18 a.m.
NEDg Description generation batch_69d20f2aa6588190b842641d41f6179a completed April 5, 2026, 7:28 a.m.
NED2 Entity disambiguation (via description) batch_69d20f7c328c8190a58ad56e9e63cba0 completed April 5, 2026, 7:30 a.m.
Created at: March 30, 2026, 8:05 p.m.