Triple

T20333447
Position Surface form Disambiguated ID Type / Status
Subject Paradice project E492542 entity
Predicate creates P490 FINISHED
Object Crakers 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: Crakers | Statement: [Paradice project, creates, Crakers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Crakers
Context triple: [Paradice project, creates, Crakers]
  • A. Crakers chosen
    The Crakers are a group of genetically engineered post-human beings in Margaret Atwood’s MaddAddam trilogy, designed to be peaceful, environmentally harmonious replacements for humanity.
  • B. Crookers
    Crookers is an Italian DJ and production duo known for their influential electro-house and fidget house remixes and club tracks.
  • C. Creepers
    Creepers is a 2005 thriller novel by David Morrell that follows a group of urban explorers whose night inside an abandoned hotel turns into a deadly struggle for survival.
  • D. Krew
    Krew is a notorious, overweight crime boss and black-market dealer in Haven City from the Jak and Daxter video game series.
  • E. The Lurkers
    The Lurkers are a British punk rock band formed in the 1970s, known for their raw sound and status as one of the early groups on the UK punk scene.
  • 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_69e0b4a1a09881908d97270d6971a25a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e677e94e2481908898e0a3513e1209 completed April 20, 2026, 7 p.m.
Created at: April 16, 2026, 11:22 a.m.