Triple

T21598640
Position Surface form Disambiguated ID Type / Status
Subject Jim Steinman E532968 entity
Predicate wroteFor P1996 FINISHED
Object Air Supply 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: Air Supply | Statement: [Jim Steinman, wroteFor, Air Supply]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Air Supply
Context triple: [Jim Steinman, wroteFor, Air Supply]
  • A. Air Supply chosen
    Air Supply is a soft rock duo from Australia, best known for their string of romantic power ballads that gained international popularity in the late 1970s and 1980s.
  • B. Shalamar
    Shalamar is an American R&B and soul music group best known for their smooth harmonies and influential dance hits in the late 1970s and 1980s.
  • C. Savage Garden
    Savage Garden was an Australian pop duo known for their melodic, radio-friendly hits in the late 1990s and early 2000s, including songs like "Truly Madly Deeply" and "I Want You."
  • D. Kool & the Gang
    Kool & the Gang is an American R&B, soul, funk, and disco band best known for hits like "Celebration," "Jungle Boogie," and "Ladies' Night."
  • E. Wet Wet Wet
    Wet Wet Wet is a Scottish pop band best known internationally for their hit cover of “Love Is All Around” and a string of successful chart singles in the late 1980s and 1990s.
  • 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_69e0c46364608190a337dc8720dc2a35 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eefae2fc908190b989f39e8cefffb2 completed April 27, 2026, 5:57 a.m.
Created at: April 16, 2026, 6:32 p.m.