Triple

T2388722
Position Surface form Disambiguated ID Type / Status
Subject Dracula E48891 entity
Predicate author P4 FINISHED
Object Bram Stoker E50289 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 | Statement: [Dracula, author, Bram Stoker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bram Stoker
Context triple: [Dracula, author, Bram Stoker]
  • A. Bram Stoker chosen
    Bram Stoker was an Irish author best known for his 1897 novel "Dracula," a foundational work of Gothic horror fiction.
  • B. Sheridan Le Fanu
    Sheridan Le Fanu was a 19th-century Irish writer best known for his influential Gothic and ghost stories, including the vampire novella "Carmilla."
  • C. Gaston Leroux
    Gaston Leroux was a French journalist and novelist best known as the author of the classic mystery novel "The Phantom of the Opera."
  • D. James Branch Cabell
    James Branch Cabell was an American author best known for his ironic and fantastical novels set in the mythical province of Poictesme, particularly the once-controversial book "Jurgen, A Comedy of Justice."
  • E. Anne Rice
    Anne Rice was a bestselling American author renowned for her gothic horror and erotic novels, particularly "The Vampire Chronicles" series featuring the vampire Lestat.
  • 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_69a88aa5f63081908d07fd302029fcbd completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc7dca9248190b634ae9e02f6899a completed March 7, 2026, 6:38 a.m.
NED1 Entity disambiguation (via context triple) batch_69aeb3d2ad588190a2cf3adab6a9404d completed March 9, 2026, 11:49 a.m.
Created at: March 4, 2026, 7:57 p.m.