Triple

T995288
Position Surface form Disambiguated ID Type / Status
Subject Roy Scheider E21481 entity
Predicate spouse P13 FINISHED
Object Cynthia Scheider
Cynthia Scheider is an American film editor known for her work on movies such as "The Taking of Pelham One Two Three" and "Kramer vs. Kramer."
E232695 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: Cynthia Scheider | Statement: [Roy Scheider, spouse, Cynthia Scheider]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cynthia Scheider
Context triple: [Roy Scheider, spouse, Cynthia Scheider]
  • A. Joanne Schieble
    Joanne Schieble is an American woman best known as the biological mother of Apple co-founder Steve Jobs.
  • B. Fern Kraemer
    Fern Kraemer was a party to the landmark U.S. Supreme Court case Shelley v. Kraemer, which held that courts could not enforce racially restrictive housing covenants.
  • C. Annette Ziegler
    Annette Ziegler is an American jurist who serves as the Chief Justice of the Wisconsin Supreme Court.
  • D. Roberta Seidman
    Roberta Seidman was the wife of American actor John Garfield, a prominent film star of the 1930s and 1940s.
  • E. Barbara Pewterschmidt
    Barbara Pewterschmidt is Lois Griffin’s wealthy, snobbish mother and Stewie Griffin’s maternal grandmother in the animated series "Family Guy."
  • 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: Cynthia Scheider
Triple: [Roy Scheider, spouse, Cynthia Scheider]
Generated description
Cynthia Scheider is an American film editor known for her work on movies such as "The Taking of Pelham One Two Three" and "Kramer vs. Kramer."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Cynthia Scheider
Target entity description: Cynthia Scheider is an American film editor known for her work on movies such as "The Taking of Pelham One Two Three" and "Kramer vs. Kramer."
  • A. Joanne Schieble
    Joanne Schieble is an American woman best known as the biological mother of Apple co-founder Steve Jobs.
  • B. Fern Kraemer
    Fern Kraemer was a party to the landmark U.S. Supreme Court case Shelley v. Kraemer, which held that courts could not enforce racially restrictive housing covenants.
  • C. Annette Ziegler
    Annette Ziegler is an American jurist who serves as the Chief Justice of the Wisconsin Supreme Court.
  • D. Roberta Seidman
    Roberta Seidman was the wife of American actor John Garfield, a prominent film star of the 1930s and 1940s.
  • E. Barbara Pewterschmidt
    Barbara Pewterschmidt is Lois Griffin’s wealthy, snobbish mother and Stewie Griffin’s maternal grandmother in the animated series "Family Guy."
  • 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_69a4b4c75de88190bf7fec7a053f7a90 completed March 1, 2026, 9:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69ae26ce527c8190988fd9a97ad06895 completed March 9, 2026, 1:47 a.m.
NEDg Description generation batch_69ae2763b4b08190b733e8342a52f75e completed March 9, 2026, 1:50 a.m.
NED2 Entity disambiguation (via description) batch_69ae27d10bf08190a14fa1ca906646f8 completed March 9, 2026, 1:52 a.m.
Created at: March 1, 2026, 7:41 p.m.