Triple

T23439053
Position Surface form Disambiguated ID Type / Status
Subject Bornholm Airport E565344 entity
Predicate IATAcode P418 FINISHED
Object RNN
RNN is the IATA airport code for Bornholm Airport, which serves the Danish island of Bornholm.
 E1585026 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: RNN | Statement: [Bornholm Airport, IATAcode, RNN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: RNN
Context triple: [Bornholm Airport, IATAcode, RNN]
  • A. recurrent neural networks
    Recurrent neural networks are a class of artificial neural networks designed to process sequential data by maintaining and updating a hidden state that captures information over time.
  • B. LSTM networks
    LSTM networks are a type of recurrent neural network architecture designed to effectively capture long-term dependencies in sequential data by using gated memory cells.
  • C. GRU
    GRU is the IATA airport code for São Paulo–Guarulhos International Airport, the main international gateway serving São Paulo, Brazil.
  • D. GRU
    GRU is the abbreviation for the Georgian Rugby Union, the governing body responsible for overseeing and developing rugby union in Georgia.
  • E. GRU
    GRU is Russia’s military intelligence agency, known for conducting espionage, cyber operations, and covert activities abroad.
  • 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: RNN
Triple: [Bornholm Airport, IATAcode, RNN]
Generated description
RNN is the IATA airport code for Bornholm Airport, which serves the Danish island of Bornholm.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: RNN
Target entity description: RNN is the IATA airport code for Bornholm Airport, which serves the Danish island of Bornholm.
  • A. recurrent neural networks
    Recurrent neural networks are a class of artificial neural networks designed to process sequential data by maintaining and updating a hidden state that captures information over time.
  • B. LSTM networks
    LSTM networks are a type of recurrent neural network architecture designed to effectively capture long-term dependencies in sequential data by using gated memory cells.
  • C. GRU
    GRU is the IATA airport code for São Paulo–Guarulhos International Airport, the main international gateway serving São Paulo, Brazil.
  • D. GRU
    GRU is the abbreviation for the Georgian Rugby Union, the governing body responsible for overseeing and developing rugby union in Georgia.
  • E. GRU
    GRU is Russia’s military intelligence agency, known for conducting espionage, cyber operations, and covert activities abroad.
  • 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_69e24584f9488190bb32730bd2ce023e completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1a5de713c8190b35bfa66dddbd5af completed April 29, 2026, 6:31 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c67b363e08190b4fe2011a42f7835 completed May 19, 2026, 1:37 p.m.
NEDg Description generation batch_6a0c72171580819097c9f287d501ae7e completed May 19, 2026, 2:22 p.m.
NED2 Entity disambiguation (via description) batch_6a0c76f0f4bc81909912d2196e969cf1 completed May 19, 2026, 2:42 p.m.
Created at: April 17, 2026, 5:50 p.m.