Triple

T6981710
Position Surface form Disambiguated ID Type / Status
Subject Trondheim Airport, Værnes E161861 entity
Predicate hasIATAcode P2569 FINISHED
Object TRD
TRD is the IATA airport code for Trondheim Airport, Værnes, the main international airport serving Trondheim, Norway.
E632522 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: TRD | Statement: [Trondheim Airport, Værnes, hasIATAcode, TRD]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TRD
Context triple: [Trondheim Airport, Værnes, hasIATAcode, TRD]
  • A. TRD Pro
    TRD Pro is an off-road-focused performance trim level offered by Toyota, featuring enhanced suspension, rugged styling, and specialized equipment for improved capability on rough terrain.
  • B. TRC
    TRC is the premier annual international rugby union competition in the Southern Hemisphere, contested by Argentina, Australia, New Zealand, and South Africa.
  • C. TRC
    TRC is the commonly used acronym for South Africa’s Truth and Reconciliation Commission, a post-apartheid body established to investigate human rights abuses and promote national healing.
  • D. TRG
    TRG is the IATA airport code for Tauranga Airport in Tauranga, New Zealand.
  • E. TR
    TR is the common abbreviation for the Textus Receptus, a historically influential printed Greek New Testament text that underlies many early Protestant Bible translations.
  • 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: TRD
Triple: [Trondheim Airport, Værnes, hasIATAcode, TRD]
Generated description
TRD is the IATA airport code for Trondheim Airport, Værnes, the main international airport serving Trondheim, Norway.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: TRD
Target entity description: TRD is the IATA airport code for Trondheim Airport, Værnes, the main international airport serving Trondheim, Norway.
  • A. TRD Pro
    TRD Pro is an off-road-focused performance trim level offered by Toyota, featuring enhanced suspension, rugged styling, and specialized equipment for improved capability on rough terrain.
  • B. TRC
    TRC is the premier annual international rugby union competition in the Southern Hemisphere, contested by Argentina, Australia, New Zealand, and South Africa.
  • C. TRC
    TRC is the commonly used acronym for South Africa’s Truth and Reconciliation Commission, a post-apartheid body established to investigate human rights abuses and promote national healing.
  • D. TRG
    TRG is the IATA airport code for Tauranga Airport in Tauranga, New Zealand.
  • E. TR
    TR is the common abbreviation for the Textus Receptus, a historically influential printed Greek New Testament text that underlies many early Protestant Bible translations.
  • 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_69c68855dc0481909b4c7e9e9ed273db completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6db6d3f3c8190b0121f7934440c34 completed March 27, 2026, 7:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69c761c0ecd88190a684392aa6daf267 completed March 28, 2026, 5:06 a.m.
NEDg Description generation batch_69c76275a5f08190b71a59694ef4a1fd completed March 28, 2026, 5:09 a.m.
NED2 Entity disambiguation (via description) batch_69c762ee1a048190ada3e6fd850e468b completed March 28, 2026, 5:11 a.m.
Created at: March 27, 2026, 2:31 p.m.