Triple

T15184761
Position Surface form Disambiguated ID Type / Status
Subject The Public Enemy E362838 entity
Predicate starring P1507 FINISHED
Object Mae Clarke E274387 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: Mae Clarke | Statement: [The Public Enemy, starring, Mae Clarke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mae Clarke
Context triple: [The Public Enemy, starring, Mae Clarke]
  • A. Mae Clarke chosen
    Mae Clarke was an American film actress best known for her roles in early 1930s Hollywood classics, including Frankenstein and The Public Enemy.
  • B. Rosanna Hoult
    Rosanna Hoult is a British actress known for her work in film and television and as the sister of actor Nicholas Hoult.
  • C. Rebecca Ferguson
    Rebecca Ferguson is a British television producer known for her work on high-profile drama series, including the BBC political scandal drama "The Trial of Christine Keeler."
  • D. Rebecca Ferguson
    Rebecca Ferguson is a Swedish actress known for her versatile performances in films such as the Mission: Impossible series, The Greatest Showman, and Dune.
  • E. Saskia Reeves
    Saskia Reeves is a British actress known for her work in film, television, and theatre, including roles in series such as "Luther" and numerous acclaimed stage productions.
  • 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_69d85a09a39c81908759f23268e2d408 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e006674c088190ba635a78c30f5637 completed April 15, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69fec893f1e08190a192b7b9b80484e8 completed May 9, 2026, 5:39 a.m.
Created at: April 10, 2026, 3:09 a.m.