Triple

T15950908
Position Surface form Disambiguated ID Type / Status
Subject Sons of Soul E386814 entity
Predicate hasPart P35 FINISHED
Object Leavin' E386808 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: Leavin' | Statement: [Sons of Soul, hasPart, Leavin']
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leavin'
Context triple: [Sons of Soul, hasPart, Leavin']
  • A. Leavin' chosen
    "Leavin'" is an R&B song by the American group Tony! Toni! Toné! known for its smooth vocals and soulful, early-1990s sound.
  • B. Leavin'
    "Leavin'" is a 2008 pop-R&B single by American singer Jesse McCartney that became one of his biggest commercial hits.
  • C. A Lesson in Leavin'
    "A Lesson in Leavin'" is a popular country song best known for Dottie West's hit 1980 recording about a woman warning a cheating lover he'll eventually get what he deserves.
  • D. Whole Lot of Leavin'
    "Whole Lot of Leavin'" is a country rock song by Bon Jovi from their 2007 album "Lost Highway."
  • E. Wouldn’t Leave
    "Wouldn’t Leave" is a melodic, emotionally driven song by Kanye West (Ye) that reflects on loyalty, controversy, and the strain his public actions place on his personal relationships.
  • 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_69d86da882448190a82ea962fe343b79 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156d59f5081909f6a81d578c4e2e8 completed April 16, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffbe78a76481909622d7a2443cba4d completed May 9, 2026, 11:08 p.m.
Created at: April 10, 2026, 4:53 a.m.