Triple

T16438664
Position Surface form Disambiguated ID Type / Status
Subject On the Radio E399239 entity
Predicate composer P1361 FINISHED
Object Donna Summer E93370 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: Donna Summer | Statement: [On the Radio, composer, Donna Summer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Donna Summer
Context triple: [On the Radio, composer, Donna Summer]
  • A. Donna Summer chosen
    Donna Summer was an American singer, songwriter, and “Queen of Disco” whose powerful vocals and string of 1970s and 1980s dance hits made her an icon of popular music.
  • B. Gloria Gaynor
    Gloria Gaynor is an American disco and soul singer best known for her iconic 1978 hit "I Will Survive," a defining anthem of resilience and empowerment.
  • C. Barbara West
    Barbara West is an actress known for her role in the acclaimed Australian psychological horror film "The Babadook."
  • D. Minnie Riperton
    Minnie Riperton was an American soul singer best known for her five-octave vocal range and the 1975 hit single "Lovin' You."
  • E. Pia Zadora
    Pia Zadora is an American actress and singer known for her work in film, stage, and pop music, as well as for the controversy surrounding her early critical reception and Golden Globe win.
  • 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_69d87f2c6778819080fcfae53be8f12a completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32ba5a4748190b63ff53bfb5957c7 completed April 18, 2026, 6:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0139e380bc81908452f6e8666f23ad completed May 11, 2026, 2:07 a.m.
Created at: April 10, 2026, 5:10 a.m.