Triple

T19983685
Position Surface form Disambiguated ID Type / Status
Subject Robert Galbraith E493881 entity
Predicate notableWork P4 FINISHED
Object Career of Evil 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: Career of Evil | Statement: [Robert Galbraith, notableWork, Career of Evil]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Career of Evil
Context triple: [Robert Galbraith, notableWork, Career of Evil]
  • A. Career of Evil chosen
    Career of Evil is a crime novel in the Cormoran Strike detective series, published under J. K. Rowling’s pseudonym Robert Galbraith.
  • B. Man of Evil
    Man of Evil is an alternative title for the 1944 British melodrama film "Fanny by Gaslight," adapted from Michael Sadleir’s novel and set in Victorian London.
  • C. For Love of Evil
    For Love of Evil is a fantasy novel by Piers Anthony, part of his Incarnations of Immortality series, that explores the origin and role of the Incarnation of Evil.
  • D. The Evil Thereof
    The Evil Thereof is a 1915 American silent drama film written by playwright Channing Pollock that explores moral conflict and social issues of its era.
  • E. Touching Evil
    Touching Evil is a crime drama television series about an unconventional detective who returns to work after surviving a near-fatal shooting, using his unique perspective to track down dangerous criminals.
  • 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65d157d088190af861608936e59b7 completed April 20, 2026, 5:06 p.m.
Created at: April 11, 2026, 3:28 p.m.