Triple

T20958026
Position Surface form Disambiguated ID Type / Status
Subject If Not for You E516152 entity
Predicate recordLabel P1500 FINISHED
Object Festival Records 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: Festival Records | Statement: [If Not for You, recordLabel, Festival Records]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Festival Records
Context triple: [If Not for You, recordLabel, Festival Records]
  • A. Festival Records chosen
    Festival Records was a prominent Australian record label known for signing and releasing music by major artists such as Olivia Newton-John.
  • B. Parkway Records
    Parkway Records is a record label imprint best known for releasing early rock and pop music as part of the Cameo-Parkway family of labels.
  • C. Heartbeat Records
    Heartbeat Records is a record label best known for reissuing classic Jamaican reggae and ska recordings, particularly from the legendary Studio One catalog.
  • D. Fascination Records
    Fascination Records is a British pop-focused record label known for signing and promoting mainstream pop acts such as girl group The Saturdays.
  • E. Landmark Records
    Landmark Records was a jazz-focused record label known for producing albums by prominent artists such as pianist Mulgrew Miller during the 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_69e0b4fde6c48190af1398e7e734629e completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fb6d6cd48190b83d1ceb1d0f6670 completed April 21, 2026, 4:22 a.m.
Created at: April 16, 2026, 1:29 p.m.