Triple

T1379361
Position Surface form Disambiguated ID Type / Status
Subject Neil Gaiman E29300 entity
Predicate wrote P2831 FINISHED
Object Neverwhere E158658 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: Neverwhere | Statement: [Neil Gaiman, wrote, Neverwhere]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Neverwhere
Context triple: [Neil Gaiman, wrote, Neverwhere]
  • A. Neverwhere chosen
    Neverwhere is a dark urban fantasy novel by Neil Gaiman that explores a hidden, magical underworld beneath the streets of London.
  • B. The Graveyard Book
    The Graveyard Book is a darkly whimsical children's fantasy novel by Neil Gaiman about an orphaned boy raised by ghosts in a graveyard.
  • C. The Black Windmill
    The Black Windmill is a 1974 British spy thriller film directed by Don Siegel and starring Michael Caine as an MI6 agent whose son is kidnapped by arms dealers.
  • D. Wonderland
    Wonderland is a rapid transit station in Revere, Massachusetts, serving as the northern terminus of Boston’s MBTA Blue Line.
  • E. The Witch of Portobello
    The Witch of Portobello is a novel by Brazilian author Paulo Coelho that explores spirituality, identity, and the nature of love through the fragmented testimonies of people who knew its enigmatic heroine, Athena.
  • 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_69a498d883a48190bfdca525296ef7ee completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c3187f248190a5813274b0ef944d completed March 1, 2026, 10:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69ace56940408190aeba5a342ae3ab17 completed March 8, 2026, 2:56 a.m.
Created at: March 1, 2026, 7:59 p.m.