Triple

T6091830
Position Surface form Disambiguated ID Type / Status
Subject Albert Nobbs E135782 entity
Predicate starring P1507 FINISHED
Object Brenda Fricker E545338 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: Brenda Fricker | Statement: [Albert Nobbs, starring, Brenda Fricker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brenda Fricker
Context triple: [Albert Nobbs, starring, Brenda Fricker]
  • A. Brenda Fricker chosen
    Brenda Fricker is an Irish actress best known for her Academy Award–winning performance as Christy Brown’s mother in the film "My Left Foot."
  • B. Sandy Dennis
    Sandy Dennis was an American stage and film actress known for her intense, neurotic character portrayals and her Academy Award–winning performance in "Who's Afraid of Virginia Woolf?".
  • C. Kathy Bates
    Kathy Bates is an acclaimed American actress known for her powerful, often intense performances, including her Oscar-winning role in the psychological thriller "Misery."
  • D. Arlene Alda
    Arlene Alda is an American photographer, author, and former clarinetist known for her children's books and marriage to actor Alan Alda.
  • E. Edith Fricker
    Edith Fricker was the wife of English Romantic poet Robert Southey and a member of the literary Fricker family connected with several Lake Poets.
  • 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_69c0087cd3c48190b459848c72d84eb1 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c057ab7324819086d4708e6f9391c0 completed March 22, 2026, 8:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69c20d4e28b48190bb44675c5c035bd3 completed March 24, 2026, 4:04 a.m.
Created at: March 22, 2026, 4:12 p.m.