Triple

T992380
Position Surface form Disambiguated ID Type / Status
Subject Lawrence Kasdan E21419 entity
Predicate spouse P13 FINISHED
Object Meg Kasdan
Meg Kasdan is an American filmmaker and screenwriter known for her collaborative work with her husband, director Lawrence Kasdan, on several acclaimed films.
 E128326 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: Meg Kasdan | Statement: [Lawrence Kasdan, spouse, Meg Kasdan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Meg Kasdan
Context triple: [Lawrence Kasdan, spouse, Meg Kasdan]
  • A. Diane Venora
    Diane Venora is an American actress known for her intense, versatile performances in film, television, and theater, including prominent roles in works like "Heat" and "Romeo + Juliet."
  • B. Irin Carmon
    Irin Carmon is a journalist and author best known for co-writing the biography "Notorious RBG" about Supreme Court Justice Ruth Bader Ginsburg.
  • C. Karen Kempner
    Karen Kempner is an American psychiatrist best known as the mother of Facebook co-founder Mark Zuckerberg.
  • D. Jill Hornor
    Jill Hornor is an art consultant and the longtime wife of renowned cellist Yo-Yo Ma.
  • E. Dana DeMuth
    Dana DeMuth is a longtime Major League Baseball umpire who has officiated numerous postseason games, including multiple World Series.
  • 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: Meg Kasdan
Triple: [Lawrence Kasdan, spouse, Meg Kasdan]
Generated description
Meg Kasdan is an American filmmaker and screenwriter known for her collaborative work with her husband, director Lawrence Kasdan, on several acclaimed films.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Meg Kasdan
Target entity description: Meg Kasdan is an American filmmaker and screenwriter known for her collaborative work with her husband, director Lawrence Kasdan, on several acclaimed films.
  • A. Diane Venora
    Diane Venora is an American actress known for her intense, versatile performances in film, television, and theater, including prominent roles in works like "Heat" and "Romeo + Juliet."
  • B. Irin Carmon
    Irin Carmon is a journalist and author best known for co-writing the biography "Notorious RBG" about Supreme Court Justice Ruth Bader Ginsburg.
  • C. Karen Kempner
    Karen Kempner is an American psychiatrist best known as the mother of Facebook co-founder Mark Zuckerberg.
  • D. Jill Hornor
    Jill Hornor is an art consultant and the longtime wife of renowned cellist Yo-Yo Ma.
  • E. Dana DeMuth
    Dana DeMuth is a longtime Major League Baseball umpire who has officiated numerous postseason games, including multiple World Series.
  • 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_69a493c476b48190b41fc5e793171cc6 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b4c3f7b48190a31308bdc09817c6 completed March 1, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac537d788c81908d239f102626bdd6 completed March 7, 2026, 4:34 p.m.
NEDg Description generation batch_69ac544fc41881908daff6b313622619 completed March 7, 2026, 4:37 p.m.
NED2 Entity disambiguation (via description) batch_69ac5526679081909c9f7458bd316ff6 completed March 7, 2026, 4:41 p.m.
Created at: March 1, 2026, 7:41 p.m.