Triple

T3120837
Position Surface form Disambiguated ID Type / Status
Subject Keanu Reeves E65178 entity
Predicate notableWork P4 FINISHED
Object Bram Stoker's Dracula E48891 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: Bram Stoker's Dracula | Statement: [Keanu Reeves, notableWork, Bram Stoker's Dracula]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bram Stoker's Dracula
Context triple: [Keanu Reeves, notableWork, Bram Stoker's Dracula]
  • A. Dracula chosen
    Dracula is Bram Stoker’s 1897 Gothic horror novel that introduced the iconic vampire Count Dracula and helped define modern vampire fiction.
  • B. Horror of Dracula
    Horror of Dracula is a 1958 British gothic horror film from Hammer Film Productions, renowned for its vivid color, atmospheric style, and Christopher Lee’s iconic portrayal of Count Dracula.
  • C. The Vampire
    "The Vampire" is a film featuring actress Lydia Reed, known for her work in mid-20th-century American cinema.
  • D. Stoker
    Stoker is a surname most famously associated with Bram Stoker, the Irish author of the Gothic horror novel "Dracula."
  • E. Carmilla
    Carmilla is an 1872 Gothic novella by Sheridan Le Fanu that features one of literature’s earliest and most influential lesbian vampire characters.
  • 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_69ad857fcc088190b0c4d45a5cde6f61 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada5295cd481908d52e165538c67fa completed March 8, 2026, 4:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69b20f6bc644819093a7cab7220f4ca0 completed March 12, 2026, 12:57 a.m.
Created at: March 8, 2026, 3:04 p.m.