Triple

T15355430
Position Surface form Disambiguated ID Type / Status
Subject Billund E367160 entity
Predicate airportICAO P419 FINISHED
Object EKBI
EKBI is the ICAO airport code for Billund Airport, a major international airport in Denmark serving the Jutland region and nearby attractions like Legoland.
 E1151106 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: EKBI | Statement: [Billund, airportICAO, EKBI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: EKBI
Context triple: [Billund, airportICAO, EKBI]
  • A. EBI
    EBI is a scoring system used to evaluate and rank conservation practices and land enrollment proposals based on their environmental benefits.
  • B. EKB
    EKB is the National Rail station code for Eskbank railway station in Midlothian, Scotland.
  • C. EBK
    EBK is the National Rail station code for East Bank railway station in the United Kingdom.
  • D. EGKB
    EGKB is the ICAO airport code for London Biggin Hill Airport, a historic former Royal Air Force station in Greater London, England.
  • E. BKI
    BKI is the IATA airport code for Kota Kinabalu International Airport, a major air gateway to the Malaysian state of Sabah on the island of Borneo.
  • 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: EKBI
Triple: [Billund, airportICAO, EKBI]
Generated description
EKBI is the ICAO airport code for Billund Airport, a major international airport in Denmark serving the Jutland region and nearby attractions like Legoland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: EKBI
Target entity description: EKBI is the ICAO airport code for Billund Airport, a major international airport in Denmark serving the Jutland region and nearby attractions like Legoland.
  • A. EBI
    EBI is a scoring system used to evaluate and rank conservation practices and land enrollment proposals based on their environmental benefits.
  • B. EKB
    EKB is the National Rail station code for Eskbank railway station in Midlothian, Scotland.
  • C. EBK
    EBK is the National Rail station code for East Bank railway station in the United Kingdom.
  • D. EGKB
    EGKB is the ICAO airport code for London Biggin Hill Airport, a historic former Royal Air Force station in Greater London, England.
  • E. BKI
    BKI is the IATA airport code for Kota Kinabalu International Airport, a major air gateway to the Malaysian state of Sabah on the island of Borneo.
  • 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_69d85a1483788190ad93c2748e8af34b completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e2c00648190ae2325e1ee58dcfd completed April 16, 2026, 1:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff02012fa48190a108f1ca710ffb15 completed May 9, 2026, 9:44 a.m.
NEDg Description generation batch_69ff02d0d0188190b6414a52bf8e6e54 completed May 9, 2026, 9:48 a.m.
NED2 Entity disambiguation (via description) batch_69ff037ddf1c8190b7c93c1b3edf33e8 completed May 9, 2026, 9:50 a.m.
Created at: April 10, 2026, 3:18 a.m.