Triple

T9726859
Position Surface form Disambiguated ID Type / Status
Subject Alice Brady E235635 entity
Predicate name P16 FINISHED
Object Alice Brady E235635 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: Alice Brady | Statement: [Alice Brady, name, Alice Brady]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alice Brady
Context triple: [Alice Brady, name, Alice Brady]
  • A. Alice Brady chosen
    Alice Brady was an American stage and film actress of the early 20th century, best known for her character roles in both silent and sound films and for winning an Academy Award for Best Supporting Actress.
  • B. Maud Ellen Dixon
    Maud Ellen Dixon was the wife of New Zealand physicist and science administrator Ernest Marsden.
  • C. Kate Reed
    Kate Reed is the sharp, idealistic former lawyer turned mediator at the center of the legal dramedy series "Fairly Legal."
  • D. Vivien Harmon
    Vivien Harmon is a central character in the first season of the horror anthology series American Horror Story, portrayed as a troubled wife and mother whose family moves into a haunted Los Angeles mansion.
  • E. Marguerite Roberts
    Marguerite Roberts was a prominent American screenwriter known for her sharp dialogue and work on numerous Hollywood films from the 1930s through the 1960s, including the classic Western "True Grit."
  • 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_69ca84d0fad481909cdd45aa77416c48 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9e798c348190885b79d7dffc9d8d completed April 1, 2026, 10:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19fb208a48190864f8f085da83db7 completed April 4, 2026, 11:33 p.m.
Created at: March 30, 2026, 8:21 p.m.