Triple

T2426348
Position Surface form Disambiguated ID Type / Status
Subject Maryon Pearson E53536 entity
Predicate familyName P18 FINISHED
Object Pearson E32445 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: Pearson | Statement: [Maryon Pearson, familyName, Pearson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pearson
Context triple: [Maryon Pearson, familyName, Pearson]
  • A. Pearson chosen
    Pearson is a major British multinational publishing and education company known for its textbooks, assessments, and digital learning solutions worldwide.
  • B. Prentice Hall
    Prentice Hall is a major American educational and professional publishing company known for its textbooks and academic titles across a wide range of disciplines.
  • C. McGraw-Hill
    McGraw-Hill is a major American educational publishing company known for producing textbooks and academic resources across a wide range of disciplines.
  • D. Cengage Learning
    Cengage Learning is a major educational content and technology company that produces textbooks, digital learning solutions, and course materials for higher education and professional markets worldwide.
  • E. Houghton Mifflin
    Houghton Mifflin is a major American publishing company known for its educational materials, textbooks, and notable works of fiction and non-fiction.
  • 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_69ab495c44d48190b7235b23719bc3f6 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abc99b95548190b77d36de9adfe3bb completed March 7, 2026, 6:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69aebf637be4819096874a24e87f84ab completed March 9, 2026, 12:38 p.m.
Created at: March 6, 2026, 9:42 p.m.