Triple

T5020612
Position Surface form Disambiguated ID Type / Status
Subject Nîmes-Alès-Camargue-Cévennes Airport E112839 entity
Predicate IATAcode P418 FINISHED
Object FNI
FNI is the IATA airport code for Nîmes-Alès-Camargue-Cévennes Airport in southern France.
 E485810 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: FNI | Statement: [Nîmes-Alès-Camargue-Cévennes Airport, IATAcode, FNI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FNI
Context triple: [Nîmes-Alès-Camargue-Cévennes Airport, IATAcode, FNI]
  • A. FNS
    FNS is the U.S. Department of Agriculture agency that administers federal food assistance and nutrition programs such as SNAP and school meals.
  • B. FNC
    FNC is the IATA airport code for Cristiano Ronaldo Madeira International Airport, the main air gateway to Portugal’s Madeira Island.
  • C. FNM
    FNM was the former stock ticker symbol for Fannie Mae, the U.S. government-sponsored enterprise that provides liquidity and stability to the mortgage market.
  • D. FNIA
    FNIA is the commonly used acronym for "Football Night in America," NBC's flagship Sunday night NFL pregame show and broadcast.
  • E. FNWI
    FNWI is the Faculty of Science of the University of Amsterdam, encompassing a broad range of natural sciences, mathematics, and computer science education and research.
  • 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: FNI
Triple: [Nîmes-Alès-Camargue-Cévennes Airport, IATAcode, FNI]
Generated description
FNI is the IATA airport code for Nîmes-Alès-Camargue-Cévennes Airport in southern France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FNI
Target entity description: FNI is the IATA airport code for Nîmes-Alès-Camargue-Cévennes Airport in southern France.
  • A. FNS
    FNS is the U.S. Department of Agriculture agency that administers federal food assistance and nutrition programs such as SNAP and school meals.
  • B. FNC
    FNC is the IATA airport code for Cristiano Ronaldo Madeira International Airport, the main air gateway to Portugal’s Madeira Island.
  • C. FNM
    FNM was the former stock ticker symbol for Fannie Mae, the U.S. government-sponsored enterprise that provides liquidity and stability to the mortgage market.
  • D. FNIA
    FNIA is the commonly used acronym for "Football Night in America," NBC's flagship Sunday night NFL pregame show and broadcast.
  • E. FNWI
    FNWI is the Faculty of Science of the University of Amsterdam, encompassing a broad range of natural sciences, mathematics, and computer science education and research.
  • 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_69bd4435c2f48190be593158cbfcf8a3 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd736399ac8190aa38efc4b4edc6a2 completed March 20, 2026, 4:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69be927f4ad0819096826f6cb141c90b completed March 21, 2026, 12:43 p.m.
NEDg Description generation batch_69be92e7304081909747a34dff7f9e25 completed March 21, 2026, 12:45 p.m.
NED2 Entity disambiguation (via description) batch_69be935872a88190adec17789298e01a completed March 21, 2026, 12:47 p.m.
Created at: March 20, 2026, 1:36 p.m.