Triple

T17883678
Position Surface form Disambiguated ID Type / Status
Subject The Kindly Ones E447150 entity
Predicate featuresCharacter P626 FINISHED
Object Matthew the Raven 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: Matthew the Raven | Statement: [The Kindly Ones, featuresCharacter, Matthew the Raven]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matthew the Raven
Context triple: [The Kindly Ones, featuresCharacter, Matthew the Raven]
  • A. Matthew the Raven chosen
    Matthew the Raven is a talking raven who serves as a loyal emissary and companion to Dream in Neil Gaiman’s comic series "The Sandman."
  • B. Philip Raven
    Philip Raven is a cold, efficient professional hitman and the morally ambiguous antihero of the film noir "This Gun for Hire."
  • C. Bartholomew Batts
    Bartholomew Batts is an editor known for his work on the book "The Return of Dr. Fu Manchu."
  • D. Raven
    Raven is a minor character appearing in the "Genesis of the Daleks" serial from the long-running British science fiction television series Doctor Who.
  • E. Raven
    Raven is a fictional character who appears in the comic series "Old Wounds," serving as a key figure in its narrative.
  • 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49c11530881908ad98fbd0a52b1c3 completed April 19, 2026, 9:10 a.m.
Created at: April 10, 2026, 10:18 a.m.