Triple

T22978499
Position Surface form Disambiguated ID Type / Status
Subject Hiromi E571390 entity
Predicate hasRecordedWith P20941 FINISHED
Object Hiromi’s Sonicbloom 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: Hiromi’s Sonicbloom | Statement: [Hiromi, hasRecordedWith, Hiromi’s Sonicbloom]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hiromi’s Sonicbloom
Context triple: [Hiromi, hasRecordedWith, Hiromi’s Sonicbloom]
  • A. Hiromi’s Sonicbloom chosen
    Hiromi’s Sonicbloom is a high-energy jazz fusion band led by Japanese pianist Hiromi Uehara, known for its virtuosic performances and eclectic blend of jazz, rock, and classical influences.
  • B. Sonicbloom
    Sonicbloom is a musical artist known for performing the track "Time Control."
  • C. Sone
    Sone is a Japanese surname borne by various notable figures in politics, arts, and sports.
  • D. Crystal Sound
    Crystal Sound is a professional recording studio known for hosting sessions by prominent artists such as James Taylor.
  • E. ÎleSoniq
    ÎleSoniq is an annual electronic dance music festival held in Montreal, Canada, known for featuring major international DJs and immersive stage productions.
  • 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_69e245b3c50481908bb3741ec9f40862 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18293f830819095cca91af7abd742 completed April 29, 2026, 4:01 a.m.
Created at: April 17, 2026, 3:49 p.m.