Triple

T12932051
Position Surface form Disambiguated ID Type / Status
Subject John Weitz E309407 entity
Predicate spouse P13 FINISHED
Object Susan Kohner E414276 NE FINISHED

How this triple was built (2 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: Susan Kohner | Statement: [John Weitz, spouse, Susan Kohner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susan Kohner
Context triple: [John Weitz, spouse, Susan Kohner]
  • A. Susan Kohner chosen
    Susan Kohner is an American former actress best known for her Oscar-nominated role in the 1959 film "Imitation of Life."
  • B. Susan Kobrin
    Susan Kobrin is known as the spouse of American social psychologist Ed O’Brien.
  • C. Nancy Kurshan
    Nancy Kurshan is an American activist and writer best known as a co-founder of the Youth International Party (Yippies) and for her work in prison abolition and social justice movements.
  • D. Carole Kravetz
    Carole Kravetz is a film editor known for her work on the crime thriller "One False Move."
  • E. Ilene Rosenzweig
    Ilene Rosenzweig is a writer and editor best known for co-authoring lifestyle and design books with fashion designer Cynthia Rowley.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d7bdfa933c8190b5a27aa4a08a19b7 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97dc53060819090a126f15428e411 completed April 10, 2026, 10:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7c6f404888190b7bb47bff1a7c1e1 completed May 3, 2026, 10:06 p.m.
Created at: April 9, 2026, 5:42 p.m.