Triple

T21269239
Position Surface form Disambiguated ID Type / Status
Subject Upstream E524210 entity
Predicate author P4 FINISHED
Object Mary Oliver 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: Mary Oliver | Statement: [Upstream, author, Mary Oliver]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Oliver
Context triple: [Upstream, author, Mary Oliver]
  • A. Mary Oliver chosen
    Mary Oliver was a beloved American poet renowned for her clear, contemplative verse about nature, spirituality, and the human experience.
  • B. Jane Kenyon
    Jane Kenyon was an American poet known for her clear, contemplative verse that often explored themes of rural life, spirituality, and depression.
  • C. Jorie Graham
    Jorie Graham is a Pulitzer Prize–winning American poet renowned for her intellectually rigorous, formally innovative work that explores history, perception, and the natural world.
  • D. Donald Hall
    Donald Hall was a prominent American poet, essayist, and former U.S. Poet Laureate known for his reflective, rural-themed verse and influential contributions to contemporary poetry.
  • E. W. S. Merwin
    W. S. Merwin was an influential American poet, translator, and environmental activist known for his lyrical, meditative verse and multiple Pulitzer Prize–winning collections.
  • 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_69e0b5156d7881909bd4f83676590715 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e73651115081908b5083ba818a6bb1 completed April 21, 2026, 8:33 a.m.
Created at: April 16, 2026, 4:01 p.m.