Triple

T3552099
Position Surface form Disambiguated ID Type / Status
Subject Paris–Nice E75133 entity
Predicate typicalFinishLocation P47075 FINISHED
Object Nice E2387 NE FINISHED

How this triple was built (3 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: [Paris–Nice, typicalFinishLocation, Nice]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nice
Context triple: [Paris–Nice, typicalFinishLocation, Nice]
  • A. Nice chosen
    Nice is a prominent Mediterranean coastal city on the French Riviera, known for its mild climate, beaches, and vibrant cultural life.
  • B. Nice
    Nice is a cabin class offered by Breeze Airways that provides a standard, budget-friendly economy experience for passengers.
  • 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.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: typicalFinishLocation
Context triple: [Paris–Nice, typicalFinishLocation, Nice]
  • A. typicalFinish
    Indicates that an action, process, or event commonly or characteristically ends with a particular outcome or state.
  • B. finishingArea chosen
    Indicates the location or area where an activity, process, or event comes to an end or is completed.
  • C. finalHomeOf
    Indicates that a location is the last or ultimate home, residence, or resting place of an entity.
  • D. placeOfConclusion
    Indicates the location where an event, process, or activity is brought to an end or formally concluded.
  • E. finalsLocation
    Indicates the place where the final stage or concluding event of something (such as a competition or process) takes place.
  • F. None of above.

Provenance (4 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_69ad85d33c6c819081d5ac1df13b5680 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc05256f081908b8d6a5df917e679 completed March 8, 2026, 6:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69b38bbf19808190b42c9feddc2a1030 completed March 13, 2026, 3:59 a.m.
PD Predicate disambiguation batch_69adb83270ac819083967db0570167d2 completed March 8, 2026, 5:56 p.m.
Created at: March 8, 2026, 3:20 p.m.