Triple

T14535800
Position Surface form Disambiguated ID Type / Status
Subject William Steig E341039 entity
Predicate spouse P13 FINISHED
Object Liza Steig
Liza Steig is known primarily as the wife of American cartoonist and children's book author William Steig.
E1115018 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: Liza Steig | Statement: [William Steig, spouse, Liza Steig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liza Steig
Context triple: [William Steig, spouse, Liza Steig]
  • A. Liza Weil
    Liza Weil is an American actress best known for her roles as Paris Geller on "Gilmore Girls" and Bonnie Winterbottom on "How to Get Away with Murder."
  • B. Liza Chasin
    Liza Chasin is a film and television producer known for her work on independent and studio projects, including "The Ballad of Jack and Rose."
  • C. Liza Snyder
    Liza Snyder is an American television actress best known for her comedic roles on sitcoms such as "Yes, Dear" and "Man with a Plan."
  • D. Liza Huber
    Liza Huber is an American actress best known for her role on the soap opera "Passions" and as the daughter of daytime television star Susan Lucci.
  • E. Liza Johnson
    Liza Johnson is an American film director and screenwriter known for her character-driven independent films and the historical comedy-drama "Elvis & Nixon."
  • 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: Liza Steig
Triple: [William Steig, spouse, Liza Steig]
Generated description
Liza Steig is known primarily as the wife of American cartoonist and children's book author William Steig.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Liza Steig
Target entity description: Liza Steig is known primarily as the wife of American cartoonist and children's book author William Steig.
  • A. Liza Weil
    Liza Weil is an American actress best known for her roles as Paris Geller on "Gilmore Girls" and Bonnie Winterbottom on "How to Get Away with Murder."
  • B. Liza Chasin
    Liza Chasin is a film and television producer known for her work on independent and studio projects, including "The Ballad of Jack and Rose."
  • C. Liza Snyder
    Liza Snyder is an American television actress best known for her comedic roles on sitcoms such as "Yes, Dear" and "Man with a Plan."
  • D. Liza Huber
    Liza Huber is an American actress best known for her role on the soap opera "Passions" and as the daughter of daytime television star Susan Lucci.
  • E. Liza Johnson
    Liza Johnson is an American film director and screenwriter known for her character-driven independent films and the historical comedy-drama "Elvis & Nixon."
  • 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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb1b9d39881908c7a3a5b17d432af completed April 14, 2026, 9:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdf072a46481909287ef89f226270e completed May 8, 2026, 2:17 p.m.
NEDg Description generation batch_69fdf2b6c7148190a9ff302d88890b8f completed May 8, 2026, 2:27 p.m.
NED2 Entity disambiguation (via description) batch_69fdf30dab20819085589da4e869fb7e completed May 8, 2026, 2:28 p.m.
Created at: April 10, 2026, 1:22 a.m.