Triple

T19012374
Position Surface form Disambiguated ID Type / Status
Subject Conteville family E465259 entity
Predicate hasTitle P38 FINISHED
Object Count of Mortain 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: Count of Mortain | Statement: [Conteville family, hasTitle, Count of Mortain]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Count of Mortain
Context triple: [Conteville family, hasTitle, Count of Mortain]
  • A. Count of Mortain chosen
    Count of Mortain was a noble title in medieval Normandy and England, notably held by Stephen of England before he became king.
  • B. Le Grand Macabre
    Le Grand Macabre is a darkly comic, avant-garde opera by György Ligeti that satirizes apocalypse and death through absurd, surreal scenes and an experimental musical language.
  • C. The Dead Mountaineer’s Inn
    The Dead Mountaineer’s Inn is a Soviet-era science fiction detective novel by Arkady and Boris Strugatsky that blends mystery, satire, and the uncanny in a remote mountain hotel setting.
  • D. D’entre les morts
    D’entre les morts is a 1954 French crime novel by Pierre Boileau and Thomas Narcejac that served as the literary basis for Alfred Hitchcock’s film Vertigo.
  • E. The Graveyard
    The Graveyard is a 2006 American slasher horror film about a group of friends whose deadly prank in a cemetery comes back to haunt them years later.
  • 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_69d8dd025c188190a1d81f5b4ec7e2c6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6a9bac8819093f9af57000667b0 completed April 20, 2026, 7:32 a.m.
Created at: April 10, 2026, 12:02 p.m.