Triple

T21703562
Position Surface form Disambiguated ID Type / Status
Subject A91 E535715 entity
Predicate serves P98 FINISHED
Object Fiumicino 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: Fiumicino | Statement: [A91, serves, Fiumicino]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fiumicino
Context triple: [A91, serves, Fiumicino]
  • A. Fiumicino chosen
    Fiumicino is a coastal town and comune near Rome in central Italy, best known for hosting Rome’s main international airport, Leonardo da Vinci–Fiumicino Airport.
  • B. Roma Airport
    Roma Airport is a regional Australian airport serving the town of Roma and the surrounding Surat Basin area in Queensland.
  • C. Rome Ciampino Airport
    Rome Ciampino Airport is a smaller international airport serving Rome, Italy, primarily used by low-cost carriers and charter flights.
  • D. Aeroporto di Roma–Fiumicino
    Aeroporto di Roma–Fiumicino is the main international airport serving Rome, Italy, and one of the busiest air hubs in Europe.
  • E. Leonardo da Vinci–Fiumicino Airport
    Leonardo da Vinci–Fiumicino Airport is Italy’s largest and busiest international airport, serving as the primary air gateway to Rome and a major hub for global travel.
  • 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_69e0c46b44c0819088ab883ebd44e0e8 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef9b82901c81909de242c920fbc164 completed April 27, 2026, 5:23 p.m.
Created at: April 16, 2026, 6:46 p.m.