Triple

T150296
Position Surface form Disambiguated ID Type / Status
Subject Toni Morrison E3415 entity
Predicate employer P7 FINISHED
Object Random House E8970 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: Random House | Statement: [Toni Morrison, employer, Random House]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Random House
Context triple: [Toni Morrison, employer, Random House]
  • A. Random House chosen
    Random House is a major American book publishing company known for releasing a wide range of influential fiction and nonfiction titles.
  • B. Simon & Schuster
    Simon & Schuster is a major American publishing company known for producing a wide range of bestselling fiction and nonfiction books.
  • C. Alfred A. Knopf
    Alfred A. Knopf is a prestigious American publishing house known for its high-quality literary fiction and nonfiction titles.
  • D. Harper & Row
    Harper & Row was a major American publishing house known for producing influential works in literature, education, and academic scholarship.
  • E. Little, Brown and Company
    Little, Brown and Company is a long-established American publishing house known for releasing influential works of fiction and nonfiction by prominent authors.
  • 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_69a252868de4819080e21c9938bfe8b6 completed Feb. 28, 2026, 2:27 a.m.
NER Named-entity recognition batch_69a2580dda148190a522e0ac276d5f33 completed Feb. 28, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2eb788a888190bbb53e82559abbf3 completed Feb. 28, 2026, 1:19 p.m.
Created at: Feb. 28, 2026, 2:31 a.m.