Triple

T5396542
Position Surface form Disambiguated ID Type / Status
Subject Discourses on Livy E120669 entity
Predicate focusOfBook2 P21671 FINISHED
Object expansion and military affairs of republics LITERAL 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: expansion and military affairs of republics | Statement: [Discourses on Livy, focusOfBook2, expansion and military affairs of republics]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: focusOfBook2
Context triple: [Discourses on Livy, focusOfBook2, expansion and military affairs of republics]
  • A. book2Focus chosen
    Indicates that attention, interest, or emphasis is directed toward a particular book.
  • B. book4Focus
    Indicates that something is the primary subject or focal point of a book or written work.
  • C. focusesOn
    Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
  • D. focusType
    Indicates the specific kind or category of focus or attention that is being applied to or associated with an entity or interaction.
  • E. focusPosition
    Indicates the spatial or logical position at which attention, concentration, or processing is currently directed within a given context.
  • F. None of above.

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_69bd4637b92c8190b815b6443ae4b323 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd8932b8bc8190bd31e11b167a7212 completed March 20, 2026, 5:51 p.m.
PD Predicate disambiguation batch_69bd84660ea08190a641084814fcf94d completed March 20, 2026, 5:31 p.m.
Created at: March 20, 2026, 2:04 p.m.