Triple

T22841689
Position Surface form Disambiguated ID Type / Status
Subject Emma Tallulah Behn E566097 entity
Predicate father P120 FINISHED
Object Ari Behn NE NERFINISHED

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: Ari Behn | Statement: [Emma Tallulah Behn, father, Ari Behn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ari Behn
Context triple: [Emma Tallulah Behn, father, Ari Behn]
  • A. Ari Behn chosen
    Ari Behn was a Norwegian author and playwright known for his literary works, public persona, and former marriage to Princess Märtha Louise of Norway.
  • B. Noel Behn
    Noel Behn was an American novelist, screenwriter, and theatrical producer best known for his espionage fiction and for writing the book that inspired the film "The Brink's Job."
  • C. Jodi Wexler
    Jodi Wexler is an actress best known for her role in the film "The Love Machine."
  • D. Mira Harberg
    Mira Harberg is a fictional character in the television miniseries "Irma Vep," involved in the show’s meta-narrative about filmmaking and performance.
  • E. Sarah Gurney
    Sarah Gurney was the wife of British Conservative politician Samuel Hoare Jr., later Viscount Templewood, and a member of the prominent Gurney family.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245869e188190a196584f36e682da completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17e855abc8190b9cf8cc515090a7f completed April 29, 2026, 3:44 a.m.
Created at: April 17, 2026, 3:35 p.m.