Triple

T23058816
Position Surface form Disambiguated ID Type / Status
Subject Fucino plain E574237 entity
Predicate historicalRegion P915 FINISHED
Object Marsica 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: Marsica | Statement: [Fucino plain, historicalRegion, Marsica]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marsica
Context triple: [Fucino plain, historicalRegion, Marsica]
  • A. Marsica chosen
    Marsica is a historical region in central Italy, located in the Apennine Mountains of Abruzzo and known for its ancient Italic heritage and the former Lake Fucino basin.
  • B. Marsciano
    Marsciano is a town and comune in the Umbria region of central Italy, known for its medieval historic center and agricultural surroundings.
  • C. Valascia
    Valascia was an iconic open-air ice hockey arena in Ambrì, Switzerland, renowned for its passionate atmosphere as the longtime home of HC Ambrì-Piotta.
  • D. Frescati
    Frescati is an area in northern Stockholm, Sweden, known for hosting Stockholm University and several major cultural and scientific institutions.
  • E. Petrassi
    Petrassi is an Italian surname most notably associated with the 20th-century composer Goffredo Petrassi.
  • 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_69e245ba7ae48190be606dbc54120e39 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1899e6c788190a2a862122cae8dc3 completed April 29, 2026, 4:31 a.m.
Created at: April 17, 2026, 3:55 p.m.