Triple

T23246145
Position Surface form Disambiguated ID Type / Status
Subject Book II E581586 entity
Predicate followedBy P78 FINISHED
Object Book III — 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: Book III | Statement: [Book II, followedBy, Book III]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Book III
Context triple: [Book II, followedBy, Book III]
  • A. Book III
    Book III is a component section of the Power Architecture specification that defines part of the architecture’s operational and programming model.
  • B. Book III
    Book III is the third section of Augustine’s theological treatise *On Christian Doctrine*, focusing on the principles for interpreting ambiguous or figurative passages of Scripture.
  • C. Book III
    Book III is the concluding section of Aristotle’s *Rhetoric*, focusing on style and the effective arrangement of speeches in persuasive communication.
  • D. Book III
    Book III is one of the four main divisions of the Institutes of Justinian, a foundational 6th-century Roman law textbook that systematically presents key aspects of private law.
  • E. Book III
    Book III is the concluding section of René Descartes’ La Géométrie, focusing on advanced applications of his analytic methods to solve complex geometric problems.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

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_69e24606b17c81908aba1a4911c8a8ba completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f193f0f5d88190a497f14601f9bf29 completed April 29, 2026, 5:15 a.m.
Created at: April 17, 2026, 4:10 p.m.