Triple

T5012922
Position Surface form Disambiguated ID Type / Status
Subject Carcassonne Airport E112668 entity
Predicate ICAOcode P419 FINISHED
Object LFMK
LFMK is the ICAO airport code for Carcassonne Airport in southern France, which serves the city of Carcassonne and the surrounding Occitanie region.
 E487372 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: LFMK | Statement: [Carcassonne Airport, ICAOcode, LFMK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LFMK
Context triple: [Carcassonne Airport, ICAOcode, LFMK]
  • A. LFML
    LFML is the ICAO airport code for Marseille Provence Airport, a major international airport serving the city of Marseille and the Provence region in southern France.
  • B. LFMN
    LFMN is the ICAO airport code for Nice Côte d’Azur Airport, a major international airport serving Nice and the French Riviera in southeastern France.
  • C. LM
    LM is the Apollo Lunar Module, the spacecraft used by NASA during the Apollo program to land astronauts on the Moon and return them to lunar orbit.
  • D. LM
    LM is the IATA airline designator assigned to Loganair, a regional airline based in Scotland.
  • E. 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.
  • 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: LFMK
Triple: [Carcassonne Airport, ICAOcode, LFMK]
Generated description
LFMK is the ICAO airport code for Carcassonne Airport in southern France, which serves the city of Carcassonne and the surrounding Occitanie region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LFMK
Target entity description: LFMK is the ICAO airport code for Carcassonne Airport in southern France, which serves the city of Carcassonne and the surrounding Occitanie region.
  • A. LFML
    LFML is the ICAO airport code for Marseille Provence Airport, a major international airport serving the city of Marseille and the Provence region in southern France.
  • B. LFMN
    LFMN is the ICAO airport code for Nice Côte d’Azur Airport, a major international airport serving Nice and the French Riviera in southeastern France.
  • C. LM
    LM is the Apollo Lunar Module, the spacecraft used by NASA during the Apollo program to land astronauts on the Moon and return them to lunar orbit.
  • D. LM
    LM is the IATA airline designator assigned to Loganair, a regional airline based in Scotland.
  • E. 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.
  • 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_69bd4434acb8819086679dbeccc2fe54 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd730f12a481908a27c15dc73987c6 completed March 20, 2026, 4:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69be9271eccc8190bbe9bdb876b41cb8 completed March 21, 2026, 12:43 p.m.
NEDg Description generation batch_69be9653457c819082c4e4436a940f92 completed March 21, 2026, 1 p.m.
NED2 Entity disambiguation (via description) batch_69be96b861d08190b64145f30b3420b5 completed March 21, 2026, 1:01 p.m.
Created at: March 20, 2026, 1:35 p.m.