Triple

T3231476
Position Surface form Disambiguated ID Type / Status
Subject Burgess Meredith E67748 entity
Predicate spouse P13 FINISHED
Object Margaret Perry (divorced)
Margaret Perry is known as the former wife of American actor and filmmaker Burgess Meredith.
 E339170 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: Margaret Perry (divorced) | Statement: [Burgess Meredith, spouse, Margaret Perry (divorced)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Margaret Perry (divorced)
Context triple: [Burgess Meredith, spouse, Margaret Perry (divorced)]
  • A. George Merrill (divorced)
    George Merrill is an American songwriter best known as one half of the duo Boy Meets Girl, co-writing Whitney Houston hits like "How Will I Know" and "I Wanna Dance with Somebody (Who Loves Me)."
  • B. Julia Bingham (divorced)
    Julia Bingham is the former wife of American screenwriter and director Aaron Sorkin.
  • C. Jane McIntosh (divorced)
    Jane McIntosh is best known as the former wife of English lyricist and author Tim Rice.
  • D. Sheila Kelley
    Sheila Kelley is an American actress and dancer best known for her roles in film and television and for founding the S Factor pole-dance fitness movement.
  • E. Susan Brown (divorced)
    Susan Brown is the former wife of American businessman and former New York City mayor Michael Bloomberg.
  • 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: Margaret Perry (divorced)
Triple: [Burgess Meredith, spouse, Margaret Perry (divorced)]
Generated description
Margaret Perry is known as the former wife of American actor and filmmaker Burgess Meredith.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Margaret Perry (divorced)
Target entity description: Margaret Perry is known as the former wife of American actor and filmmaker Burgess Meredith.
  • A. George Merrill (divorced)
    George Merrill is an American songwriter best known as one half of the duo Boy Meets Girl, co-writing Whitney Houston hits like "How Will I Know" and "I Wanna Dance with Somebody (Who Loves Me)."
  • B. Julia Bingham (divorced)
    Julia Bingham is the former wife of American screenwriter and director Aaron Sorkin.
  • C. Jane McIntosh (divorced)
    Jane McIntosh is best known as the former wife of English lyricist and author Tim Rice.
  • D. Sheila Kelley
    Sheila Kelley is an American actress and dancer best known for her roles in film and television and for founding the S Factor pole-dance fitness movement.
  • E. Susan Brown (divorced)
    Susan Brown is the former wife of American businessman and former New York City mayor Michael Bloomberg.
  • 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_69ad858c61888190a31196310d9b30b5 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaed99d2c8190950fa883ec6f1f8e completed March 8, 2026, 5:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2773492f88190ad97879f29875ae4 completed March 12, 2026, 8:20 a.m.
NEDg Description generation batch_69b277e70c648190af38b7939be90e67 completed March 12, 2026, 8:23 a.m.
NED2 Entity disambiguation (via description) batch_69b27879ff6081909f7d7f474d46ac4b completed March 12, 2026, 8:25 a.m.
Created at: March 8, 2026, 3:08 p.m.