Triple

T107645
Position Surface form Disambiguated ID Type / Status
Subject Orly Airport E2174 entity
Predicate ICAOcode P419 FINISHED
Object LFPO
LFPO is the ICAO airport code for Paris Orly Airport, a major international airport serving the Paris metropolitan area in France.
 E11762 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: LFPO | Statement: [Orly Airport, ICAOcode, LFPO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LFPO
Context triple: [Orly Airport, ICAOcode, LFPO]
  • A. LFPG
    LFPG is the ICAO airport code for Paris Charles de Gaulle Airport, France’s largest and busiest international air hub.
  • B. LU
    LU is the two-letter ISO 3166-1 alpha-2 country code assigned to Luxembourg for international identification and data standards.
  • C. SF
    SF is the standard two-letter postal abbreviation used to represent the city of San Francisco, California.
  • D. LOC
    LOC is the commonly used abbreviation for the Library of Congress, the national library of the United States and one of the largest libraries in the world.
  • E. 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.
  • 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: LFPO
Triple: [Orly Airport, ICAOcode, LFPO]
Generated description
LFPO is the ICAO airport code for Paris Orly Airport, a major international airport serving the Paris metropolitan area in France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LFPO
Target entity description: LFPO is the ICAO airport code for Paris Orly Airport, a major international airport serving the Paris metropolitan area in France.
  • A. LFPG
    LFPG is the ICAO airport code for Paris Charles de Gaulle Airport, France’s largest and busiest international air hub.
  • B. LU
    LU is the two-letter ISO 3166-1 alpha-2 country code assigned to Luxembourg for international identification and data standards.
  • C. SF
    SF is the standard two-letter postal abbreviation used to represent the city of San Francisco, California.
  • D. LOC
    LOC is the commonly used abbreviation for the Library of Congress, the national library of the United States and one of the largest libraries in the world.
  • E. 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.
  • 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_69a24fcdaeb48190a2d796677e4b3281 completed Feb. 28, 2026, 2:15 a.m.
NER Named-entity recognition batch_69a256cac6d4819083b50c9c9d95e975 completed Feb. 28, 2026, 2:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69a27c04949481908af8c8426789bc53 completed Feb. 28, 2026, 5:24 a.m.
NEDg Description generation batch_69a27c8abcb4819091c440c63704d435 completed Feb. 28, 2026, 5:26 a.m.
NED2 Entity disambiguation (via description) batch_69a27e7633d88190a622115c4e29fd9c completed Feb. 28, 2026, 5:34 a.m.
Created at: Feb. 28, 2026, 2:20 a.m.