Triple

T15355429
Position Surface form Disambiguated ID Type / Status
Subject Billund E367160 entity
Predicate airportIATA P418 FINISHED
Object BLL
BLL is the IATA airport code for Billund Airport in Denmark, a major international gateway serving the Jutland region and nearby attractions such as Legoland.
 E1151105 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: BLL | Statement: [Billund, airportIATA, BLL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BLL
Context triple: [Billund, airportIATA, BLL]
  • A. BCL
    BCL is an abbreviation commonly used for the Oracle Binary Code License, a proprietary software license governing the use and distribution of Oracle’s binary code.
  • B. BCL
    BCL is a public library system serving the community of Beaverton, Oregon with lending materials, programs, and educational resources.
  • C. BLC
    BLC is the commonly used abbreviation for the Boston Landmarks Commission, the city agency responsible for identifying and protecting Boston’s historic buildings and districts.
  • D. BVL
    BVL is Germany’s Federal Office of Consumer Protection and Food Safety, the national authority responsible for ensuring food safety and protecting consumer health.
  • E. BL
    BL is the vehicle registration code used for the city of Banja Luka in Bosnia and Herzegovina.
  • 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: BLL
Triple: [Billund, airportIATA, BLL]
Generated description
BLL is the IATA airport code for Billund Airport in Denmark, a major international gateway serving the Jutland region and nearby attractions such as Legoland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BLL
Target entity description: BLL is the IATA airport code for Billund Airport in Denmark, a major international gateway serving the Jutland region and nearby attractions such as Legoland.
  • A. BCL
    BCL is a public library system serving the community of Beaverton, Oregon with lending materials, programs, and educational resources.
  • B. BCL
    BCL is an abbreviation commonly used for the Oracle Binary Code License, a proprietary software license governing the use and distribution of Oracle’s binary code.
  • C. BLC
    BLC is the commonly used abbreviation for the Boston Landmarks Commission, the city agency responsible for identifying and protecting Boston’s historic buildings and districts.
  • D. BVL
    BVL is Germany’s Federal Office of Consumer Protection and Food Safety, the national authority responsible for ensuring food safety and protecting consumer health.
  • E. BL
    BL is the vehicle registration code used for the city of Banja Luka in Bosnia and Herzegovina.
  • 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.