Triple

T15674571
Position Surface form Disambiguated ID Type / Status
Subject Peter Farrelly E377405 entity
Predicate spouse P13 FINISHED
Object Melinda Kocsis
Melinda Kocsis is known as the wife of American filmmaker and screenwriter Peter Farrelly, co-director of popular comedy films and the Oscar-winning "Green Book."
 E1171295 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: Melinda Kocsis | Statement: [Peter Farrelly, spouse, Melinda Kocsis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Melinda Kocsis
Context triple: [Peter Farrelly, spouse, Melinda Kocsis]
  • A. Colleen Sostorics
    Colleen Sostorics is a Canadian former ice hockey defenceman and three-time Olympic gold medallist who starred with the national women’s team.
  • B. Diana Pokorny
    Diana Pokorny is a film producer best known for her work on the fantasy adventure movie "Inkheart."
  • C. Cynthia Tudeski
    Cynthia Tudeski is a key character in the crime-comedy film "The Whole Nine Yards," known as the wife of a notorious hitman whose complicated relationships drive much of the movie’s plot.
  • D. Yvette Szekely
    Yvette Szekely was the wife of American writer and socialist intellectual Max Eastman.
  • E. Kimberly Krysiuk
    Kimberly Krysiuk is a writer known for her work on the series "Baby Mama."
  • 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: Melinda Kocsis
Triple: [Peter Farrelly, spouse, Melinda Kocsis]
Generated description
Melinda Kocsis is known as the wife of American filmmaker and screenwriter Peter Farrelly, co-director of popular comedy films and the Oscar-winning "Green Book."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Melinda Kocsis
Target entity description: Melinda Kocsis is known as the wife of American filmmaker and screenwriter Peter Farrelly, co-director of popular comedy films and the Oscar-winning "Green Book."
  • A. Colleen Sostorics
    Colleen Sostorics is a Canadian former ice hockey defenceman and three-time Olympic gold medallist who starred with the national women’s team.
  • B. Diana Pokorny
    Diana Pokorny is a film producer best known for her work on the fantasy adventure movie "Inkheart."
  • C. Cynthia Tudeski
    Cynthia Tudeski is a key character in the crime-comedy film "The Whole Nine Yards," known as the wife of a notorious hitman whose complicated relationships drive much of the movie’s plot.
  • D. Yvette Szekely
    Yvette Szekely was the wife of American writer and socialist intellectual Max Eastman.
  • E. Kimberly Krysiuk
    Kimberly Krysiuk is a writer known for her work on the series "Baby Mama."
  • 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_69d85cd2e28481909d4e975bee20872f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04f2c996c8190a9ebe0e92608feaa completed April 16, 2026, 2:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6edd85148190b6d5c3981204dd77 completed May 9, 2026, 5:29 p.m.
NEDg Description generation batch_69ff6fd9c968819098b2552a9deb0445 completed May 9, 2026, 5:33 p.m.
NED2 Entity disambiguation (via description) batch_69ff708d42448190a53b90e00721eaa5 completed May 9, 2026, 5:36 p.m.
Created at: April 10, 2026, 4:16 a.m.