Triple

T8267971
Position Surface form Disambiguated ID Type / Status
Subject Chuck Lorre E193347 entity
Predicate formerSpouse P493 FINISHED
Object Paula Smith
Paula Smith is best known as the former wife of American television producer and writer Chuck Lorre.
E722694 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: Paula Smith | Statement: [Chuck Lorre, formerSpouse, Paula Smith]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paula Smith
Context triple: [Chuck Lorre, formerSpouse, Paula Smith]
  • A. Brigid Bazlen
    Brigid Bazlen was an American film and television actress of the 1960s, known for her youthful screen presence and roles in Hollywood comedies and dramas.
  • B. Joanna Hoffman
    Joanna Hoffman is a marketing executive and former member of the original Macintosh team at Apple who later joined Steve Jobs at NeXT and is known for her influential role in shaping early personal computing products.
  • C. Susan Hay
    Susan Hay was the wife of George Ramsay, 9th Earl of Dalhousie, a Scottish nobleman and colonial administrator in British North America.
  • D. Patricia Skoglund
    Patricia Skoglund is known as the first wife of American investment banker and philanthropist Peter G. Peterson.
  • E. Carla Breuer
    Carla Breuer is a Dutch politician who serves as the mayor of the municipality of Teylingen in the Netherlands.
  • 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: Paula Smith
Triple: [Chuck Lorre, formerSpouse, Paula Smith]
Generated description
Paula Smith is best known as the former wife of American television producer and writer Chuck Lorre.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Paula Smith
Target entity description: Paula Smith is best known as the former wife of American television producer and writer Chuck Lorre.
  • A. Brigid Bazlen
    Brigid Bazlen was an American film and television actress of the 1960s, known for her youthful screen presence and roles in Hollywood comedies and dramas.
  • B. Joanna Hoffman
    Joanna Hoffman is a marketing executive and former member of the original Macintosh team at Apple who later joined Steve Jobs at NeXT and is known for her influential role in shaping early personal computing products.
  • C. Susan Hay
    Susan Hay was the wife of George Ramsay, 9th Earl of Dalhousie, a Scottish nobleman and colonial administrator in British North America.
  • D. Patricia Skoglund
    Patricia Skoglund is known as the first wife of American investment banker and philanthropist Peter G. Peterson.
  • E. Carla Breuer
    Carla Breuer is a Dutch politician who serves as the mayor of the municipality of Teylingen in the Netherlands.
  • 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_69ca82e081d48190986beaa51f498ab9 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb794fc4208190b268bc69ff2b28a9 completed March 31, 2026, 7:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd6833065c8190945e88022ad2869d completed April 1, 2026, 6:47 p.m.
NEDg Description generation batch_69cd6d52763c8190891f88d62be44786 completed April 1, 2026, 7:09 p.m.
NED2 Entity disambiguation (via description) batch_69cd7df568788190a5a219baa65a6a19 completed April 1, 2026, 8:20 p.m.
Created at: March 30, 2026, 5:50 p.m.