Triple

T6658381
Position Surface form Disambiguated ID Type / Status
Subject Suzanne E151406 entity
Predicate basedOn P98 FINISHED
Object Suzanne Verdal
Suzanne Verdal is a Canadian woman best known as the real-life muse who inspired Leonard Cohen’s song “Suzanne.”
 E653750 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: Suzanne Verdal | Statement: [Suzanne, basedOn, Suzanne Verdal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Suzanne Verdal
Context triple: [Suzanne, basedOn, Suzanne Verdal]
  • A. Suzanne Zimmer
    Suzanne Zimmer is the wife of renowned film composer Hans Zimmer and the mother of several of his children.
  • B. Anna Nolin
    Anna Nolin is an American educator and school district leader who serves as superintendent of the Newton Public Schools in Massachusetts.
  • C. Sonja Haraldsen
    Sonja Haraldsen, now Queen Sonja of Norway, is the queen consort of King Harald V and a prominent member of the Norwegian royal family known for her cultural and charitable work.
  • D. Caroline Smedvig
    Caroline Smedvig is an American public relations professional and former Boston Symphony Orchestra staff member best known as the wife of singer-songwriter James Taylor.
  • E. Suzanne Perrin
    Suzanne Perrin was the second wife of Franklin D. Roosevelt Jr., a lawyer and politician and son of U.S. President Franklin D. Roosevelt.
  • 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: Suzanne Verdal
Triple: [Suzanne, basedOn, Suzanne Verdal]
Generated description
Suzanne Verdal is a Canadian woman best known as the real-life muse who inspired Leonard Cohen’s song “Suzanne.”
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Suzanne Verdal
Target entity description: Suzanne Verdal is a Canadian woman best known as the real-life muse who inspired Leonard Cohen’s song “Suzanne.”
  • A. Suzanne Zimmer
    Suzanne Zimmer is the wife of renowned film composer Hans Zimmer and the mother of several of his children.
  • B. Anna Nolin
    Anna Nolin is an American educator and school district leader who serves as superintendent of the Newton Public Schools in Massachusetts.
  • C. Sonja Haraldsen
    Sonja Haraldsen, now Queen Sonja of Norway, is the queen consort of King Harald V and a prominent member of the Norwegian royal family known for her cultural and charitable work.
  • D. Caroline Smedvig
    Caroline Smedvig is an American public relations professional and former Boston Symphony Orchestra staff member best known as the wife of singer-songwriter James Taylor.
  • E. Suzanne Perrin
    Suzanne Perrin was the second wife of Franklin D. Roosevelt Jr., a lawyer and politician and son of U.S. President Franklin D. Roosevelt.
  • 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_69c687f5fac48190a09e4838d9c6b45d completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6b0706514819087270d1c68866e2c completed March 27, 2026, 4:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7daf7529c8190b70ac11fb4c9ba32 completed March 28, 2026, 1:43 p.m.
NEDg Description generation batch_69c7dbc1ff0c8190bc7639a74a5d3af3 completed March 28, 2026, 1:46 p.m.
NED2 Entity disambiguation (via description) batch_69c7dc6873a081908ea4e953430ec20b completed March 28, 2026, 1:49 p.m.
Created at: March 27, 2026, 2:01 p.m.