Triple

T5179853
Position Surface form Disambiguated ID Type / Status
Subject Nantes Atlantique Airport E116892 entity
Predicate ICAOcode P419 FINISHED
Object LFRS
LFRS is the ICAO airport code for Nantes Atlantique Airport, a major international airport serving the city of Nantes in western France.
 E500172 NE FINISHED

How this triple was built (4 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: LFRS | Statement: [Nantes Atlantique Airport, ICAOcode, LFRS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LFRS
Context triple: [Nantes Atlantique Airport, ICAOcode, LFRS]
  • A. FRS
    FRS is the post-nominal title used by Fellows of the Royal Society, denoting distinguished scientists elected to the United Kingdom’s national academy of sciences.
  • B. LPFR
    LPFR is the ICAO airport code for Faro Airport, the main international gateway to Portugal’s Algarve region.
  • C. FRL
    FRL is the IATA airport code for Forlì International Airport in Forlì, Italy.
  • D. LF
    LF is the commonly used abbreviation for the Linux Foundation, a nonprofit organization that supports and promotes the development of the Linux kernel and other open-source software projects.
  • E. LAF
    The Lebanese Armed Forces (LAF) are the military institution of Lebanon, responsible for defending the country’s sovereignty, maintaining internal security, and operating under a delicate sectarian balance.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: LFRS
Triple: [Nantes Atlantique Airport, ICAOcode, LFRS]
Generated description
LFRS is the ICAO airport code for Nantes Atlantique Airport, a major international airport serving the city of Nantes in western France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LFRS
Target entity description: LFRS is the ICAO airport code for Nantes Atlantique Airport, a major international airport serving the city of Nantes in western France.
  • A. FRS
    FRS is the post-nominal title used by Fellows of the Royal Society, denoting distinguished scientists elected to the United Kingdom’s national academy of sciences.
  • B. LPFR
    LPFR is the ICAO airport code for Faro Airport, the main international gateway to Portugal’s Algarve region.
  • C. FRL
    FRL is the IATA airport code for Forlì International Airport in Forlì, Italy.
  • D. LF
    LF is the commonly used abbreviation for the Linux Foundation, a nonprofit organization that supports and promotes the development of the Linux kernel and other open-source software projects.
  • E. LAF
    The Lebanese Armed Forces (LAF) are the military institution of Lebanon, responsible for defending the country’s sovereignty, maintaining internal security, and operating under a delicate sectarian balance.
  • F. None of above. chosen

Provenance (5 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_69bd446140f08190becb93c61158f27f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd79978a208190b2e5909795108327 completed March 20, 2026, 4:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69bed9553bc0819082a37a83a3edf7e8 completed March 21, 2026, 5:45 p.m.
NEDg Description generation batch_69bedae9de2081909bd5e872fc0f904e completed March 21, 2026, 5:52 p.m.
NED2 Entity disambiguation (via description) batch_69bedba410448190bffab466812daa7e completed March 21, 2026, 5:55 p.m.
Created at: March 20, 2026, 1:45 p.m.