Triple

T3870734
Position Surface form Disambiguated ID Type / Status
Subject Banksy E91978 entity
Predicate created P538 FINISHED
Object Dismaland E396343 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: Dismaland | Statement: [Banksy, created, Dismaland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dismaland
Context triple: [Banksy, created, Dismaland]
  • A. Dismaland chosen
    Dismaland was a temporary, dystopian “bemusement park” art installation in Weston-super-Mare, England, created by the street artist Banksy as a dark satire of consumer culture and theme-park entertainment.
  • B. Marwencol
    Marwencol is a 2010 documentary film that follows Mark Hogancamp, a man who copes with trauma by building and photographing an intricate World War II-era miniature town in his backyard.
  • C. Isles of Wonder
    Isles of Wonder was the theatrical, cinematic-themed opening ceremony of the London 2012 Olympic Games, directed by Danny Boyle and celebrating British history and culture.
  • D. Altneuland
    Altneuland is a 1902 utopian novel by Theodor Herzl that envisions a modern, pluralistic Jewish state in the Land of Israel.
  • E. Millarworld
    Millarworld is a creator-owned comic book imprint and shared universe founded by writer Mark Millar, known for titles like Kick-Ass, Wanted, and Kingsman: The Secret Service.
  • 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_69aed9645f348190a9868e7cef56ab7e completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeec54b0848190a8d4a0e4df7b6227 completed March 9, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b51c83512c81908db2e442b7d2aca0 completed March 14, 2026, 8:29 a.m.
Created at: March 9, 2026, 3:20 p.m.