Triple

T22654658
Position Surface form Disambiguated ID Type / Status
Subject Harriet Backer E559192 entity
Predicate fullName P16 FINISHED
Object Harriet Backer 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: Harriet Backer | Statement: [Harriet Backer, fullName, Harriet Backer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harriet Backer
Context triple: [Harriet Backer, fullName, Harriet Backer]
  • A. Harriet Backer chosen
    Harriet Backer was a prominent Norwegian painter known for her richly colored interior scenes and significant contribution to 19th-century Scandinavian art.
  • B. Louisa Krause
    Louisa Krause is an American actress known for her work in independent films and television, including a starring role in the 2018 psychological horror film "Skin."
  • C. Harriet B. Helberg
    Harriet B. Helberg is an American casting director and the mother of actor and comedian Simon Helberg.
  • D. Harriet Dyer
    Harriet Dyer is an Australian actress known for her work in television and film, including prominent roles in series like "Love Child" and the horror-thriller genre.
  • E. Martha Nielsen
    Martha Nielsen is a central character in the German sci-fi thriller series "Dark," whose complex relationships and time-travel entanglements are pivotal to the show's overarching mystery.
  • 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_69e245489dd88190b1f674acf61c8769 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1765a97ac819095f21ccbdada1d0a completed April 29, 2026, 3:09 a.m.
Created at: April 17, 2026, 3:06 p.m.