Triple

T18380058
Position Surface form Disambiguated ID Type / Status
Subject Amy Prentiss E446418 entity
Predicate mainCharacter P1183 FINISHED
Object Amy Prentiss 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: Amy Prentiss | Statement: [Amy Prentiss, mainCharacter, Amy Prentiss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amy Prentiss
Context triple: [Amy Prentiss, mainCharacter, Amy Prentiss]
  • A. Amy Prentiss chosen
    Amy Prentiss is a 1970s American television crime drama series featuring Jessica Walter as a pioneering female chief of detectives in San Francisco.
  • B. Ann Prentiss
    Ann Prentiss was an American character actress known for her supporting roles in film and television during the 1960s and 1970s.
  • C. Nora Prentiss
    Nora Prentiss is a 1947 film noir drama centered on a nightclub singer whose affair with a married doctor leads to deception and tragedy.
  • D. Dolores Avery
    Dolores Avery is the mother of Steven Avery, prominently featured in the true-crime documentary series "Making a Murderer" for her steadfast support of her son amid his legal battles.
  • E. Beth Seaton
    Beth Seaton is a central character in the 1978 equestrian drama film "International Velvet," serving as one of the key figures in the protagonist's journey through competitive horse riding.
  • 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_69d8b9f370b88190b1e5081c2c238e7f completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e5179aa328819097f5ed8193cfa401 completed April 19, 2026, 5:57 p.m.
Created at: April 10, 2026, 10:45 a.m.