Triple

T23336834
Position Surface form Disambiguated ID Type / Status
Subject Reus Airport E591613 entity
Predicate ICAOcode P419 FINISHED
Object LERS
LERS is the ICAO airport code for Reus Airport, a public international airport serving the city of Reus and the nearby Costa Daurada region in Catalonia, Spain.
 E1579958 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: LERS | Statement: [Reus Airport, ICAOcode, LERS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LERS
Context triple: [Reus Airport, ICAOcode, LERS]
  • A. LRS
    LRS is the IATA airport code for Leros Municipal Airport, a small regional airport serving the Greek island of Leros in the Dodecanese.
  • B. LRS
    LRS is the commonly used abbreviation for London River Services, the body responsible for coordinating and licensing passenger boat services on the River Thames in London.
  • C. LSR
    LSR is a prestigious women’s college in New Delhi, India, renowned for its academic excellence and affiliation with the University of Delhi.
  • D. LER
    LER is the vehicle registration code assigned to the German island municipality of Borkum.
  • E. LER
    LER is the National Rail station code for Leytonstone High Road railway station in London.
  • 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: LERS
Triple: [Reus Airport, ICAOcode, LERS]
Generated description
LERS is the ICAO airport code for Reus Airport, a public international airport serving the city of Reus and the nearby Costa Daurada region in Catalonia, Spain.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LERS
Target entity description: LERS is the ICAO airport code for Reus Airport, a public international airport serving the city of Reus and the nearby Costa Daurada region in Catalonia, Spain.
  • A. LRS
    LRS is the commonly used abbreviation for London River Services, the body responsible for coordinating and licensing passenger boat services on the River Thames in London.
  • B. LRS
    LRS is the IATA airport code for Leros Municipal Airport, a small regional airport serving the Greek island of Leros in the Dodecanese.
  • C. LSR
    LSR is a prestigious women’s college in New Delhi, India, renowned for its academic excellence and affiliation with the University of Delhi.
  • D. LER
    LER is the vehicle registration code assigned to the German island municipality of Borkum.
  • E. LER
    LER is the abbreviation for The Loyal Eddies, a group or organization likely centered around shared loyalty or fandom, often in a sports or community context.
  • 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_69e25d20156c81908c5c53195bd9c738 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f197f1e0588190bf073b92be0bf9e4 completed April 29, 2026, 5:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c4cb282d081908ed8fa395460d7db completed May 19, 2026, 11:42 a.m.
NEDg Description generation batch_6a0c4f634a70819088f627f13bdfe7da completed May 19, 2026, 11:54 a.m.
NED2 Entity disambiguation (via description) batch_6a0c4fc72a9c8190862256fac24682a1 completed May 19, 2026, 11:55 a.m.
Created at: April 17, 2026, 5:17 p.m.