Triple

T4420997
Position Surface form Disambiguated ID Type / Status
Subject Tiksi E95095 entity
Predicate hasIATACode P2569 FINISHED
Object IKS
IKS is the IATA airport code for Tiksi Airport, which serves the settlement of Tiksi in the Sakha Republic of Russia.
E437579 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: IKS | Statement: [Tiksi, hasIATACode, IKS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: IKS
Context triple: [Tiksi, hasIATACode, IKS]
  • A. IXS
    IXS is the three-letter IATA airport code assigned to Silchar Airport in Assam, India.
  • B. KIX
    KIX is the three-letter IATA airport code for Kansai International Airport serving the Osaka region of Japan.
  • C. IKSR
    IKSR is the German abbreviation for the International Commission for the Protection of the Rhine, an international body coordinating efforts to protect and sustainably manage the Rhine River and its basin.
  • D. IKAR
    IKAR is the former brand name of the Russian airline now known as Pegas Fly, which operates domestic and international passenger services.
  • E. IKA
    IKA is the three-letter IATA airport code for Tehran Imam Khomeini International Airport, the main international gateway serving Tehran, Iran.
  • 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: IKS
Triple: [Tiksi, hasIATACode, IKS]
Generated description
IKS is the IATA airport code for Tiksi Airport, which serves the settlement of Tiksi in the Sakha Republic of Russia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: IKS
Target entity description: IKS is the IATA airport code for Tiksi Airport, which serves the settlement of Tiksi in the Sakha Republic of Russia.
  • A. IXS
    IXS is the three-letter IATA airport code assigned to Silchar Airport in Assam, India.
  • B. KIX
    KIX is the three-letter IATA airport code for Kansai International Airport serving the Osaka region of Japan.
  • C. IKSR
    IKSR is the German abbreviation for the International Commission for the Protection of the Rhine, an international body coordinating efforts to protect and sustainably manage the Rhine River and its basin.
  • D. IKAR
    IKAR is the former brand name of the Russian airline now known as Pegas Fly, which operates domestic and international passenger services.
  • E. IKA
    IKA is the three-letter IATA airport code for Tehran Imam Khomeini International Airport, the main international gateway serving Tehran, Iran.
  • 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_69b3453a36908190b95a79a297ca083c completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b35521e020819099e72b9e2ccbd36d completed March 13, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69b5f62715748190abceb14396ad637d completed March 14, 2026, 11:58 p.m.
NEDg Description generation batch_69b5f6d4bb84819081512aec6b49507b completed March 15, 2026, 12:01 a.m.
NED2 Entity disambiguation (via description) batch_69b5f7887cb08190bf498eefc3627bfa completed March 15, 2026, 12:04 a.m.
Created at: March 12, 2026, 11:30 p.m.