Triple

T16113397
Position Surface form Disambiguated ID Type / Status
Subject Annemasse Aerodrome E390936 entity
Predicate ICAOcode P419 FINISHED
Object LFLI
LFLI is the ICAO airport code for Annemasse Aerodrome, a small regional airfield serving the Annemasse area in southeastern France near the Swiss border.
E1194467 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: LFLI | Statement: [Annemasse Aerodrome, ICAOcode, LFLI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: LFLI
Context triple: [Annemasse Aerodrome, ICAOcode, LFLI]
  • A. LFLC
    LFLC is the ICAO airport code for Clermont-Ferrand Auvergne Airport in central France.
  • B. LFLX
    LFLX is the ICAO airport code for Châteauroux-Centre "Marcel Dassault" Airport in central France, a facility known for cargo operations, aircraft maintenance, and pilot training.
  • C. LFL
    LFL is the Legends Football League, a women's American football league featuring teams such as the Chicago Bliss.
  • D. LFL
    LFL is the former New York Stock Exchange ticker symbol for LAN Airlines, a major Chilean airline that later became part of LATAM Airlines Group.
  • E. YFLI
    YFLI is the ICAO airport code for Flinders Island Airport in Tasmania, Australia.
  • 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: LFLI
Triple: [Annemasse Aerodrome, ICAOcode, LFLI]
Generated description
LFLI is the ICAO airport code for Annemasse Aerodrome, a small regional airfield serving the Annemasse area in southeastern France near the Swiss border.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: LFLI
Target entity description: LFLI is the ICAO airport code for Annemasse Aerodrome, a small regional airfield serving the Annemasse area in southeastern France near the Swiss border.
  • A. LFLC
    LFLC is the ICAO airport code for Clermont-Ferrand Auvergne Airport in central France.
  • B. LFLX
    LFLX is the ICAO airport code for Châteauroux-Centre "Marcel Dassault" Airport in central France, a facility known for cargo operations, aircraft maintenance, and pilot training.
  • C. LFL
    LFL is the Legends Football League, a women's American football league featuring teams such as the Chicago Bliss.
  • D. LFL
    LFL is the former New York Stock Exchange ticker symbol for LAN Airlines, a major Chilean airline that later became part of LATAM Airlines Group.
  • E. YFLI
    YFLI is the ICAO airport code for Flinders Island Airport in Tasmania, Australia.
  • 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_69d87f1a8dd881909f1de6ef78849874 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e20168bf98819093c3260d4fde2b53 completed April 17, 2026, 9:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffeba90ffc81909d5eb8f0cfa9f147 completed May 10, 2026, 2:21 a.m.
NEDg Description generation batch_69ffec6ce4e881908b530a981375cc55 completed May 10, 2026, 2:24 a.m.
NED2 Entity disambiguation (via description) batch_69ffed469a5c8190932fa4ebc44358c4 completed May 10, 2026, 2:28 a.m.
Created at: April 10, 2026, 5 a.m.