Triple

T4290318
Position Surface form Disambiguated ID Type / Status
Subject Terminal 2 (Nice Côte d’Azur Airport) E97372 entity
Predicate servesCity P82 FINISHED
Object Nice E2387 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: Nice | Statement: [Terminal 2 (Nice Côte d’Azur Airport), servesCity, Nice]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nice
Context triple: [Terminal 2 (Nice Côte d’Azur Airport), servesCity, Nice]
  • A. Nice
    Nice is a cabin class offered by Breeze Airways that provides a standard, budget-friendly economy experience for passengers.
  • B. Nice chosen
    Nice is a prominent Mediterranean coastal city on the French Riviera, known for its mild climate, beaches, and vibrant cultural life.
  • C. Nice Agreement
    The Nice Agreement is an international treaty that establishes a standardized classification system of goods and services used for the registration of trademarks.
  • D. FRIENDLY
    FRIENDLY is the airline callsign used by Southern Airways Express, a U.S.-based commuter and regional airline.
  • E. KIND
    KIND is the ICAO airport code for Indianapolis International Airport, a major commercial airport serving Indianapolis, Indiana, in the United States.
  • 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_69b3454595848190a0e6bbb6a2bea040 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b35061f5448190b3356b29a9129160 completed March 12, 2026, 11:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5d06ccbf081908bc23b5f194b9587 completed March 14, 2026, 9:17 p.m.
Created at: March 12, 2026, 11:08 p.m.