Triple

T20390016
Position Surface form Disambiguated ID Type / Status
Subject The Dead Don’t Die E498059 entity
Predicate starring P1507 FINISHED
Object Sara Driver 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: Sara Driver | Statement: [The Dead Don’t Die, starring, Sara Driver]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sara Driver
Context triple: [The Dead Don’t Die, starring, Sara Driver]
  • A. Sara Driver chosen
    Sara Driver is an American filmmaker and producer known for her work in New York’s independent cinema scene and her collaborations with director Jim Jarmusch.
  • B. Sally Beauman
    Sally Beauman was a British journalist and bestselling novelist known for works such as "Rebecca’s Tale" and "Destiny."
  • C. Aviva Baumann
    Aviva Baumann is an American actress best known for her role as Nicola in the comedy film "Superbad."
  • D. Elizabeth Dowdeswell
    Elizabeth Dowdeswell is a Canadian public servant and former Under-Secretary-General of the United Nations who has served as the 29th Lieutenant Governor of Ontario.
  • E. Lissa Evans
    Lissa Evans is a British author and former television director and producer, known for her witty, character-driven novels for both adults and children.
  • 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6790e65a081909832855758fffd14 completed April 20, 2026, 7:05 p.m.
Created at: April 16, 2026, 11:28 a.m.