Triple

T18978309
Position Surface form Disambiguated ID Type / Status
Subject Too Pure E464353 entity
Predicate signedArtist P16560 FINISHED
Object Mouse on Mars 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: Mouse on Mars | Statement: [Too Pure, signedArtist, Mouse on Mars]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mouse on Mars
Context triple: [Too Pure, signedArtist, Mouse on Mars]
  • A. Mouse on Mars chosen
    Mouse on Mars is an experimental German electronic music duo known for their innovative blend of IDM, techno, and avant-pop.
  • B. Matmos
    Matmos is an experimental electronic music duo known for their innovative use of unconventional sound sources and conceptual compositions.
  • C. The Notwist
    The Notwist is a German indie rock band known for blending elements of electronic music, post-rock, and experimental sounds into their evolving style.
  • D. Alborosie
    Alborosie is an Italian-born reggae artist and producer known for his roots-influenced sound and prominent role in contemporary Jamaican reggae music.
  • E. Sunz of Man
    Sunz of Man is a Wu-Tang Clan-affiliated hip hop group known for its gritty, spiritual, and socially conscious lyricism.
  • 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_69d8dd008af48190a97ff1c6488edf1b completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d621e3e08190b2d1d969ecaa380b completed April 20, 2026, 7:30 a.m.
Created at: April 10, 2026, noon