Triple

T22668147
Position Surface form Disambiguated ID Type / Status
Subject Meena Harris E559846 entity
Predicate relative P37 FINISHED
Object Maya Harris 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: Maya Harris | Statement: [Meena Harris, relative, Maya Harris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maya Harris
Context triple: [Meena Harris, relative, Maya Harris]
  • A. Maya Harris chosen
    Maya Harris is an American lawyer, public policy advocate, and political strategist who has served as a senior advisor on major Democratic campaigns and in civil rights organizations.
  • B. Tyasha Harris
    Tyasha Harris is an American professional basketball player and standout point guard who starred for the University of South Carolina Gamecocks women’s basketball program.
  • C. Courtney Harrell
    Courtney Harrell is an American songwriter and producer known for her work with major pop and R&B artists.
  • D. Jhaniele Fowler
    Jhaniele Fowler is an elite Jamaican netball goal shooter renowned for her dominant scoring ability in international competitions and professional leagues.
  • E. Mia Braswell
    Mia Braswell is an actress known for playing a young version of Rebecca Pearson on the television series "This Is Us."
  • 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_69e2454a158c819093b8e35f5045efb6 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1781de1d48190947cb1bb9d0890d9 completed April 29, 2026, 3:16 a.m.
Created at: April 17, 2026, 3:09 p.m.