Triple

T18440515
Position Surface form Disambiguated ID Type / Status
Subject Warren Ellis E450513 entity
Predicate notableWork P4 FINISHED
Object Fell 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: Fell | Statement: [Warren Ellis, notableWork, Fell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fell
Context triple: [Warren Ellis, notableWork, Fell]
  • A. Fell chosen
    Fell is a noir-inspired horror comic book series written by Warren Ellis and illustrated by Ben Templesmith, known for its grim, self-contained crime stories set in the decaying city of Snowtown.
  • B. Fell
    Fell is a surname of English and Scandinavian origin borne by various notable individuals across politics, arts, and other fields.
  • C. Wind Fell
    Wind Fell is a hill in the Ettrick Hills range of the Southern Uplands in Scotland, known for its open moorland and upland walking routes.
  • D. Rock Fall
    Rock Fall was a talented American Thoroughbred racehorse known for his impressive sprinting ability and graded stakes victories before his career was tragically cut short.
  • E. The Falling
    The Falling is a 2014 British drama film set in a girls' school in the 1960s, exploring mass hysteria and adolescent sexuality, in which Monica Dolan plays a key role.
  • 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_69d8d381d6388190a9e94e9c658174e4 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e51c10a86c819091196968b648fc92 completed April 19, 2026, 6:16 p.m.
Created at: April 10, 2026, 11:30 a.m.