Triple

T15693957
Position Surface form Disambiguated ID Type / Status
Subject Alta Airport E380406 entity
Predicate ICAO code P419 FINISHED
Object ENAT
ENAT is the ICAO airport code for Alta Airport, a regional airport in Alta, Norway.
E1171108 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: ENAT | Statement: [Alta Airport, ICAO code, ENAT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ENAT
Context triple: [Alta Airport, ICAO code, ENAT]
  • A. ENAT
    ENAT is Mexico’s National School of Theatrical Arts, a leading institution dedicated to professional training in theater and performance.
  • B. ENAS
    ENAS (Efficient Neural Architecture Search) is a method that dramatically reduces the computational cost of neural architecture search by sharing parameters among many candidate architectures within a single super-network.
  • C. ENRA
    ENRA is the ICAO airport code for Mo i Rana Airport, Røssvoll in Norway.
  • D. ENEA
    ENEA is Italy’s national agency for new technologies, energy, and sustainable economic development, focused on research and innovation in fields such as energy, environment, and advanced technologies.
  • E. ENA
    ENA is a prestigious French grande école that trained many of the country’s top civil servants and political leaders.
  • 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: ENAT
Triple: [Alta Airport, ICAO code, ENAT]
Generated description
ENAT is the ICAO airport code for Alta Airport, a regional airport in Alta, Norway.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: ENAT
Target entity description: ENAT is the ICAO airport code for Alta Airport, a regional airport in Alta, Norway.
  • A. ENAT
    ENAT is Mexico’s National School of Theatrical Arts, a leading institution dedicated to professional training in theater and performance.
  • B. ENAS
    ENAS (Efficient Neural Architecture Search) is a method that dramatically reduces the computational cost of neural architecture search by sharing parameters among many candidate architectures within a single super-network.
  • C. ENRA
    ENRA is the ICAO airport code for Mo i Rana Airport, Røssvoll in Norway.
  • D. ENEA
    ENEA is Italy’s national agency for new technologies, energy, and sustainable economic development, focused on research and innovation in fields such as energy, environment, and advanced technologies.
  • E. ENA
    ENA is a prestigious French grande école that trained many of the country’s top civil servants and political leaders.
  • 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_69d86d99e860819094b6957cde470f2c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f4f5a888190bd3681bcb9bbc02f completed April 16, 2026, 2:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6eed9a8c8190a57ffce61a27ec17 completed May 9, 2026, 5:29 p.m.
NEDg Description generation batch_69ff7097adec8190ad5fc00fa57e3383 completed May 9, 2026, 5:36 p.m.
NED2 Entity disambiguation (via description) batch_69ff70f97eec8190a1f5affdad31f2b2 completed May 9, 2026, 5:38 p.m.
Created at: April 10, 2026, 4:44 a.m.