Triple

T20223494
Position Surface form Disambiguated ID Type / Status
Subject Harriet Mary Walter E495317 entity
Predicate notableWork P4 FINISHED
Object Killing Eve 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: Killing Eve | Statement: [Harriet Mary Walter, notableWork, Killing Eve]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Killing Eve
Context triple: [Harriet Mary Walter, notableWork, Killing Eve]
  • A. Killing Eve chosen
    Killing Eve is a critically acclaimed British spy thriller television series that follows the obsessive cat-and-mouse game between an intelligence investigator and a skilled assassin.
  • B. Eye in the Sky
    Eye in the Sky is a 2015 British thriller film that explores the moral and legal complexities of modern drone warfare and targeted killings.
  • C. The Kill List
    The Kill List is a contemporary thriller novel by Frederick Forsyth that follows an elite tracker hunting a mysterious jihadist terrorist known as "the Preacher."
  • D. Red Sparrow
    Red Sparrow is a 2018 spy thriller film in which Jennifer Lawrence plays a Russian ballerina-turned-intelligence operative trained in seduction and manipulation.
  • E. Quantico
    Quantico is a small town in Prince William County, Virginia, best known for hosting the Marine Corps Base Quantico and several major U.S. federal law enforcement training facilities.
  • 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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66fd827708190b798a30f4e7d533f completed April 20, 2026, 6:26 p.m.
Created at: April 11, 2026, 11:39 p.m.