Triple

T5122871
Position Surface form Disambiguated ID Type / Status
Subject Ptuj E115510 entity
Predicate romanName P6662 FINISHED
Object Poetovio E261600 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: Poetovio | Statement: [Ptuj, romanName, Poetovio]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Poetovio
Context triple: [Ptuj, romanName, Poetovio]
  • A. Poetovio chosen
    Poetovio was a major Roman military and commercial center located in the province of Pannonia, in what is now Ptuj, Slovenia.
  • B. Poá
    Poá is a municipality in the eastern part of the São Paulo metropolitan region in Brazil, known for its residential character and proximity to the capital city.
  • C. The Poet
    "The Poet" is a seminal essay by Ralph Waldo Emerson that explores the nature, role, and visionary power of the poet in society and in expressing universal truths.
  • D. The Poet
    The Poet is a reflective, storytelling character in Henry Wadsworth Longfellow’s narrative poem collection "Tales of a Wayside Inn," representing the voice of the poet among the gathered guests.
  • E. The Poet
    The Poet is a crime novel by Michael Connelly that follows a journalist investigating a series of murders staged to look like suicides, marking one of Connelly’s most acclaimed standalone works.
  • 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_69bd4442ade0819087b9461f892b206b completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd78045e448190961db0ca7692370e completed March 20, 2026, 4:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69bec4b401a481909abf6660401c47dc completed March 21, 2026, 4:17 p.m.
Created at: March 20, 2026, 1:42 p.m.