Triple

T1813940
Position Surface form Disambiguated ID Type / Status
Subject DeVon Harris E40392 entity
Predicate knownFor P22 FINISHED
Object So High E204541 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: So High | Statement: [DeVon Harris, knownFor, So High]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: So High
Context triple: [DeVon Harris, knownFor, So High]
  • A. So High
    "So High" is an R&B/soul song by John Legend from his debut album "Get Lifted."
  • B. So High chosen
    "So High" is a creative work associated with DeVon Harris, likely recognized as one of his most prominent or influential projects.
  • C. How Low
    "How Low" is a popular hip-hop single by American rapper Ludacris, known for its catchy hook and heavy club-oriented production.
  • D. Reach Higher
    Reach Higher is an education initiative launched by Michelle Obama to inspire and support young people in pursuing and completing postsecondary education.
  • E. If Not Higher
    "If Not Higher" is a classic Yiddish short story by I. L. Peretz that gently satirizes religious hypocrisy while celebrating genuine piety and compassion.
  • 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_69a88643a3388190a612f2ebe1fb29e7 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa65c905ec8190bea7cd72d218487a completed March 6, 2026, 5:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69adc9aa4c5881908b21829dda45da5a completed March 8, 2026, 7:10 p.m.
Created at: March 4, 2026, 7:32 p.m.