Triple

T5054174
Position Surface form Disambiguated ID Type / Status
Subject Saul Bellow E113857 entity
Predicate spouse P13 FINISHED
Object Anita Goshkin
Anita Goshkin was the first wife of Nobel Prize–winning American novelist Saul Bellow.
E497516 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: Anita Goshkin | Statement: [Saul Bellow, spouse, Anita Goshkin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anita Goshkin
Context triple: [Saul Bellow, spouse, Anita Goshkin]
  • A. Valentina Brodsky
    Valentina Brodsky was the second wife of renowned modernist painter Marc Chagall, with whom she spent his later years in France.
  • B. Elka Ostrovsky
    Elka Ostrovsky is a sharp-tongued, eccentric elderly woman and main character on the sitcom "Hot in Cleveland," portrayed by Betty White.
  • C. Nina Bushkin
    Nina Bushkin was the wife of renowned American lyricist and playwright Alan Jay Lerner.
  • D. Helene Shapiro
    Helene Shapiro is an American mathematician known for her work in linear algebra and matrix theory, and as a student of Olga Taussky-Todd.
  • E. Kadya Molodowsky
    Kadya Molodowsky was a prominent 20th-century Yiddish poet, prose writer, and educator known for her innovative, often feminist-inflected contributions to modern Yiddish literature.
  • 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: Anita Goshkin
Triple: [Saul Bellow, spouse, Anita Goshkin]
Generated description
Anita Goshkin was the first wife of Nobel Prize–winning American novelist Saul Bellow.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Anita Goshkin
Target entity description: Anita Goshkin was the first wife of Nobel Prize–winning American novelist Saul Bellow.
  • A. Valentina Brodsky
    Valentina Brodsky was the second wife of renowned modernist painter Marc Chagall, with whom she spent his later years in France.
  • B. Elka Ostrovsky
    Elka Ostrovsky is a sharp-tongued, eccentric elderly woman and main character on the sitcom "Hot in Cleveland," portrayed by Betty White.
  • C. Nina Bushkin
    Nina Bushkin was the wife of renowned American lyricist and playwright Alan Jay Lerner.
  • D. Helene Shapiro
    Helene Shapiro is an American mathematician known for her work in linear algebra and matrix theory, and as a student of Olga Taussky-Todd.
  • E. Kadya Molodowsky
    Kadya Molodowsky was a prominent 20th-century Yiddish poet, prose writer, and educator known for her innovative, often feminist-inflected contributions to modern Yiddish literature.
  • 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_69bd443aa1f88190abb992d138f2cf42 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd742a59448190918766c261cfa13d completed March 20, 2026, 4:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69becfb4215c819086d0f4b412de9f2d completed March 21, 2026, 5:04 p.m.
NEDg Description generation batch_69bed224e45481909bd7a830529798d6 completed March 21, 2026, 5:15 p.m.
NED2 Entity disambiguation (via description) batch_69bed277f1c4819081a5a855c7c48809 completed March 21, 2026, 5:16 p.m.
Created at: March 20, 2026, 1:38 p.m.