Triple

T2461449
Position Surface form Disambiguated ID Type / Status
Subject Frances Ha E54542 entity
Predicate starring P1507 FINISHED
Object Michael Zegen
Michael Zegen is an American actor known for his roles in independent films and television series such as "The Marvelous Mrs. Maisel" and "Boardwalk Empire."
E268520 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: Michael Zegen | Statement: [Frances Ha, starring, Michael Zegen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Zegen
Context triple: [Frances Ha, starring, Michael Zegen]
  • A. Andrew Miano
    Andrew Miano is an American film producer known for his work on independent and critically acclaimed movies, often collaborating with director Tom Ford and others.
  • B. Joel Stransky
    Joel Stransky is a former South African rugby union fly-half best known for kicking the winning drop goal in the 1995 Rugby World Cup final.
  • C. Sebastian Maltz
    Sebastian Maltz is an actor known for his role in the television drama series "Patrick Melrose."
  • D. Michael Cerenzie
    Michael Cerenzie is a film producer known for his work on independent and genre films in Hollywood.
  • E. Michael Klein
    Michael Klein is the father of Canadian author and activist Naomi Klein.
  • 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: Michael Zegen
Triple: [Frances Ha, starring, Michael Zegen]
Generated description
Michael Zegen is an American actor known for his roles in independent films and television series such as "The Marvelous Mrs. Maisel" and "Boardwalk Empire."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Michael Zegen
Target entity description: Michael Zegen is an American actor known for his roles in independent films and television series such as "The Marvelous Mrs. Maisel" and "Boardwalk Empire."
  • A. Andrew Miano
    Andrew Miano is an American film producer known for his work on independent and critically acclaimed movies, often collaborating with director Tom Ford and others.
  • B. Joel Stransky
    Joel Stransky is a former South African rugby union fly-half best known for kicking the winning drop goal in the 1995 Rugby World Cup final.
  • C. Sebastian Maltz
    Sebastian Maltz is an actor known for his role in the television drama series "Patrick Melrose."
  • D. Michael Cerenzie
    Michael Cerenzie is a film producer known for his work on independent and genre films in Hollywood.
  • E. Michael Klein
    Michael Klein is the father of Canadian author and activist Naomi Klein.
  • 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_69ab49dee84c819096b50a0049c347ac completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd11c47408190b10c7f6a151f2db2 completed March 7, 2026, 7:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69aef0d2b2748190b12611863d8bf4ad completed March 9, 2026, 4:09 p.m.
NEDg Description generation batch_69aef3f1fb9481909748308457e6e3df completed March 9, 2026, 4:23 p.m.
NED2 Entity disambiguation (via description) batch_69aef8398fd08190821e9503c01af80a completed March 9, 2026, 4:41 p.m.
Created at: March 6, 2026, 9:44 p.m.