Triple

T11832047
Position Surface form Disambiguated ID Type / Status
Subject Mrs. Miniver E281415 entity
Predicate starring P1507 FINISHED
Object Dame May Whitty E402981 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: Dame May Whitty | Statement: [Mrs. Miniver, starring, Dame May Whitty]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dame May Whitty
Context triple: [Mrs. Miniver, starring, Dame May Whitty]
  • A. Dame May Whitty chosen
    Dame May Whitty was a distinguished English stage and film actress, renowned for her character roles in British and Hollywood cinema during the early 20th century.
  • B. Peggy Ashcroft
    Peggy Ashcroft was a distinguished English stage and film actress renowned for her Shakespearean performances and her long, influential career in British theatre.
  • C. Billie Whitelaw
    Billie Whitelaw was an acclaimed English actress renowned for her intense stage and screen performances, particularly in the plays of Samuel Beckett.
  • D. Edith Lesley
    Edith Lesley was an American educator and founder of the teacher-training institution that evolved into Lesley University in Cambridge, Massachusetts.
  • E. Anne Lewis
    Anne Lewis is a tough, principled Detroit police officer and RoboCop’s closest human partner and ally in the RoboCop franchise.
  • 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_69d6ab276f8c8190b1966a0ef11349ac completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a62c95988190a45dbaa7001c8846 completed April 10, 2026, 7:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69f16741d9a08190b6d6d5e59dfa41b8 completed April 29, 2026, 2:04 a.m.
Created at: April 8, 2026, 9:43 p.m.