Triple

T23262175
Position Surface form Disambiguated ID Type / Status
Subject Nayvadius DeMun Wilburn E582044 entity
Predicate notableWork P4 FINISHED
Object Jumpman 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: Jumpman | Statement: [Nayvadius DeMun Wilburn, notableWork, Jumpman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jumpman
Context triple: [Nayvadius DeMun Wilburn, notableWork, Jumpman]
  • A. Jumpman chosen
    "Jumpman" is a 2015 trap hit by Drake and Future, known for its catchy hook and heavy production that helped cement both artists’ dominance in modern hip-hop.
  • B. Jumpman
    Jumpman is the iconic silhouette logo of Michael Jordan in mid-air, widely recognized as the symbol of the Air Jordan brand and Nike’s basketball heritage.
  • C. Grand Jump
    Grand Jump is a Japanese seinen manga magazine known for serializing a variety of mature-themed manga titles aimed at adult readers.
  • D. Mario Bros.
    Mario Bros. is a classic 1983 arcade platform game by Nintendo featuring Mario and Luigi battling creatures in underground sewers.
  • E. Donkey Konga
    Donkey Konga is a rhythm-based music video game for the Nintendo GameCube featuring Donkey Kong characters and bongo drum controllers.
  • 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_69e246079f58819085eaa9c260906880 completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f194c9f33c819082ef6b380fc594dd completed April 29, 2026, 5:19 a.m.
Created at: April 17, 2026, 4:11 p.m.