Triple

T17563769
Position Surface form Disambiguated ID Type / Status
Subject Perusia E427756 entity
Predicate knownAsInLatin P45453 FINISHED
Object Perusia 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: Perusia | Statement: [Perusia, knownAsInLatin, Perusia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Perusia
Context triple: [Perusia, knownAsInLatin, Perusia]
  • A. Perusia chosen
    Perusia was an important ancient Etruscan city in central Italy, later known as the Roman colony of Perusia and modern-day Perugia.
  • B. Eteläsatama
    Eteläsatama is Helsinki’s central South Harbour, a key maritime hub and scenic waterfront area serving ferries, cruise ships, and seaside promenades near the city center.
  • C. Amerruki
    Amerruki is a Berber-language term used in Morocco, likely referring to a specific name or designation within Amazigh (Berber) culture.
  • D. Usonia
    Usonia is Frank Lloyd Wright’s concept for an affordable, distinctly American style of residential architecture that emphasizes simplicity, harmony with nature, and efficient use of space and materials.
  • E. D’Amérique
    D’Amérique is a modernist artwork by French avant-garde artist Francis Picabia, reflecting his experimental approach within the Dada and early abstract movements.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d889e0385081908a04b66f4dd4bd0d completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4592bde448190bf5ed2340440e2b7 completed April 19, 2026, 4:25 a.m.
Created at: April 10, 2026, 5:50 a.m.