Triple

T1361360
Position Surface form Disambiguated ID Type / Status
Subject Alan Jay Lerner E29103 entity
Predicate spouse P13 FINISHED
Object Nancy Olson
Nancy Olson is an American actress best known for her Academy Award–nominated role in the classic film "Sunset Boulevard."
E177422 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: Nancy Olson | Statement: [Alan Jay Lerner, spouse, Nancy Olson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nancy Olson
Context triple: [Alan Jay Lerner, spouse, Nancy Olson]
  • A. JoBeth Williams
    JoBeth Williams is an American actress known for her roles in films such as "Poltergeist," "The Big Chill," and numerous television movies and series.
  • B. Cindy Williams
    Cindy Williams was an American actress best known for her role as Shirley Feeney on the hit television sitcom "Laverne & Shirley."
  • C. Maud Adams
    Maud Adams is a Swedish actress best known for her roles as Bond girls in the James Bond films "The Man with the Golden Gun" and "Octopussy."
  • D. Bonnie Swanson
    Bonnie Swanson is a recurring character on the animated sitcom Family Guy, known as Joe Swanson’s soft-spoken, long-pregnant wife and neighbor of the Griffin family.
  • E. Patty Fenn
    Patty Fenn is a television producer and key character in the film "Money Monster," where she manages the chaotic live broadcast at the center of the story.
  • 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: Nancy Olson
Triple: [Alan Jay Lerner, spouse, Nancy Olson]
Generated description
Nancy Olson is an American actress best known for her Academy Award–nominated role in the classic film "Sunset Boulevard."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Nancy Olson
Target entity description: Nancy Olson is an American actress best known for her Academy Award–nominated role in the classic film "Sunset Boulevard."
  • A. JoBeth Williams
    JoBeth Williams is an American actress known for her roles in films such as "Poltergeist," "The Big Chill," and numerous television movies and series.
  • B. Cindy Williams
    Cindy Williams was an American actress best known for her role as Shirley Feeney on the hit television sitcom "Laverne & Shirley."
  • C. Maud Adams
    Maud Adams is a Swedish actress best known for her roles as Bond girls in the James Bond films "The Man with the Golden Gun" and "Octopussy."
  • D. Bonnie Swanson
    Bonnie Swanson is a recurring character on the animated sitcom Family Guy, known as Joe Swanson’s soft-spoken, long-pregnant wife and neighbor of the Griffin family.
  • E. Patty Fenn
    Patty Fenn is a television producer and key character in the film "Money Monster," where she manages the chaotic live broadcast at the center of the story.
  • 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_69a498d77abc8190913bf57e5f51d2c4 completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c2b2fb448190bef31375169b4666 completed March 1, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad36f900848190bb00cd7ad8eada60 completed March 8, 2026, 8:44 a.m.
NEDg Description generation batch_69ad38706fcc81909e42a6a713605237 completed March 8, 2026, 8:50 a.m.
NED2 Entity disambiguation (via description) batch_69ad38c50fd8819087cce60b83017766 completed March 8, 2026, 8:52 a.m.
Created at: March 1, 2026, 7:57 p.m.