Triple

T14321379
Position Surface form Disambiguated ID Type / Status
Subject Richard Flanagan E355096 entity
Predicate spouse P13 FINISHED
Object Majda Flanagan
Majda Flanagan is the wife of acclaimed Tasmanian novelist and filmmaker Richard Flanagan.
E1093673 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: Majda Flanagan | Statement: [Richard Flanagan, spouse, Majda Flanagan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Majda Flanagan
Context triple: [Richard Flanagan, spouse, Majda Flanagan]
  • A. Crista Flanagan
    Crista Flanagan is an American actress and comedian best known for her work on the sketch series MADtv and appearances in parody films.
  • B. Francie Nolan
    Francie Nolan is the introspective, resilient young heroine and narrator of Betty Smith’s novel "A Tree Grows in Brooklyn," growing up in poverty in early 20th-century Brooklyn.
  • C. Michelle Mangan
    Michelle Mangan is an American television personality and former real estate agent best known as the wife of former Major League Baseball outfielder Johnny Damon.
  • D. Arlene Vrhel
    Arlene Vrhel is an American restaurateur best known as the longtime wife of actor Joe Mantegna.
  • E. Paula Dobriansky
    Paula Dobriansky is an American foreign policy expert and diplomat who has held several senior U.S. government positions, particularly in European and democracy-promotion 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: Majda Flanagan
Triple: [Richard Flanagan, spouse, Majda Flanagan]
Generated description
Majda Flanagan is the wife of acclaimed Tasmanian novelist and filmmaker Richard Flanagan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Majda Flanagan
Target entity description: Majda Flanagan is the wife of acclaimed Tasmanian novelist and filmmaker Richard Flanagan.
  • A. Crista Flanagan
    Crista Flanagan is an American actress and comedian best known for her work on the sketch series MADtv and appearances in parody films.
  • B. Francie Nolan
    Francie Nolan is the introspective, resilient young heroine and narrator of Betty Smith’s novel "A Tree Grows in Brooklyn," growing up in poverty in early 20th-century Brooklyn.
  • C. Michelle Mangan
    Michelle Mangan is an American television personality and former real estate agent best known as the wife of former Major League Baseball outfielder Johnny Damon.
  • D. Arlene Vrhel
    Arlene Vrhel is an American restaurateur best known as the longtime wife of actor Joe Mantegna.
  • E. Paula Dobriansky
    Paula Dobriansky is an American foreign policy expert and diplomat who has held several senior U.S. government positions, particularly in European and democracy-promotion 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_69d8278ed42c8190b9f882dcce611347 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de883bf71c8190a9a092a025cf98f0 completed April 14, 2026, 6:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd468e263c81909d7261bcfd949579 completed May 8, 2026, 2:12 a.m.
NEDg Description generation batch_69fd4811e2808190b559d8348079ae8f completed May 8, 2026, 2:18 a.m.
NED2 Entity disambiguation (via description) batch_69fd48d827488190b4a494d4da64ba51 completed May 8, 2026, 2:22 a.m.
Created at: April 10, 2026, 1:13 a.m.