Triple

T15368032
Position Surface form Disambiguated ID Type / Status
Subject Armchair Expert E367466 entity
Predicate notableGuest P10756 FINISHED
Object Esther Perel E1153128 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: Esther Perel | Statement: [Armchair Expert, notableGuest, Esther Perel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Esther Perel
Context triple: [Armchair Expert, notableGuest, Esther Perel]
  • A. Esther Perel chosen
    Esther Perel is a Belgian psychotherapist and bestselling author renowned for her influential work on modern relationships, intimacy, and infidelity.
  • B. Laura Perls
    Laura Perls was a German-born psychotherapist and co-founder of Gestalt therapy, known for her influential work in humanistic and experiential psychotherapy.
  • C. Amy Koppelman
    Amy Koppelman is an American novelist and screenwriter known for her dark, psychologically driven works exploring depression, motherhood, and mental illness, including the novel "I Smile Back."
  • D. Marilyn Yalom
    Marilyn Yalom was an American cultural historian and feminist scholar known for her influential works on the history of women, sexuality, and the body.
  • E. Anna Koppelman
    Anna Koppelman is the daughter of American screenwriter, director, and producer Brian Koppelman.
  • 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_69d85a1483788190ad93c2748e8af34b completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e4a7cdc8190b7b48c97e774c306 completed April 16, 2026, 1:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff13457418819088232270b092c969 completed May 9, 2026, 10:58 a.m.
Created at: April 10, 2026, 3:18 a.m.