Triple

T9592310
Position Surface form Disambiguated ID Type / Status
Subject Farrar, Straus and Giroux E231448 entity
Predicate hasPublished P80 FINISHED
Object Jorie Graham E458237 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: Jorie Graham | Statement: [Farrar, Straus and Giroux, hasPublished, Jorie Graham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jorie Graham
Context triple: [Farrar, Straus and Giroux, hasPublished, Jorie Graham]
  • A. Jorie Graham chosen
    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.
  • B. C. D. Wright
    C. D. Wright was an American poet known for her innovative, genre-blurring work that often explored place, justice, and the voices of marginalized communities.
  • C. Kay Young
    Kay Young was a British actress known for her stage and film work in the mid-20th century.
  • D. Frank Bidart
    Frank Bidart is an acclaimed American poet known for his psychologically intense, formally inventive work that has earned him major literary honors, including the National Book Award for Poetry.
  • E. Doug Mahon
    Doug Mahon is a technology entrepreneur best known as a founder of the data storage company Seagate Technology.
  • 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_69ca8482884481908eccdfdf64d6fbf7 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9a11ec7081908dc580de2f369706 completed April 1, 2026, 10:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1791e330881908a6ad31a5bdbccec completed April 4, 2026, 8:48 p.m.
Created at: March 30, 2026, 8:07 p.m.