Triple

T16914615
Position Surface form Disambiguated ID Type / Status
Subject Etruscan League E410289 entity
Predicate member P10 FINISHED
Object Perusia E427756 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: Perusia | Statement: [Etruscan League, member, Perusia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Perusia
Context triple: [Etruscan League, member, 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 (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_69d886c7b1e481908c3766dfa8c13458 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3ca3f1a2c8190a512ccc09a080eb4 completed April 18, 2026, 6:15 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c7be679c8190b9d0b0b9cfe185d3 completed May 10, 2026, 6 p.m.
Created at: April 10, 2026, 5:30 a.m.