Triple

T9082478
Position Surface form Disambiguated ID Type / Status
Subject Irkutsk International Airport E217667 entity
Predicate ICAOcode P419 FINISHED
Object UIII
UIII is the ICAO airport code for Irkutsk International Airport, a major airport serving the city of Irkutsk in eastern Siberia, Russia.
 E775701 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: UIII | Statement: [Irkutsk International Airport, ICAOcode, UIII]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: UIII
Context triple: [Irkutsk International Airport, ICAOcode, UIII]
  • A. UIT
    UIT is the IATA airport code for the airfield serving Jaluit Atoll in the Marshall Islands.
  • B. UIKit
    UIKit is Apple’s primary user interface framework for building and managing iOS app UIs, handling views, controls, event handling, and application infrastructure.
  • C. UIP
    UIP (United International Pictures) is a major international film distribution company that has historically handled overseas releases for major Hollywood studios such as Paramount and Universal.
  • D. UI
    UI is the commonly used abbreviation for the University of Iceland, the country’s leading public research university located in Reykjavík.
  • E. UI
    UI is the commonly used abbreviation for the University of Indonesia, one of the country’s leading public universities.
  • 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: UIII
Triple: [Irkutsk International Airport, ICAOcode, UIII]
Generated description
UIII is the ICAO airport code for Irkutsk International Airport, a major airport serving the city of Irkutsk in eastern Siberia, Russia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: UIII
Target entity description: UIII is the ICAO airport code for Irkutsk International Airport, a major airport serving the city of Irkutsk in eastern Siberia, Russia.
  • A. UIT
    UIT is the IATA airport code for the airfield serving Jaluit Atoll in the Marshall Islands.
  • B. UIKit
    UIKit is Apple’s primary user interface framework for building and managing iOS app UIs, handling views, controls, event handling, and application infrastructure.
  • C. UIP
    UIP (United International Pictures) is a major international film distribution company that has historically handled overseas releases for major Hollywood studios such as Paramount and Universal.
  • D. UI
    UI is the commonly used abbreviation for the University of Indonesia, one of the country’s leading public universities.
  • E. UI
    UI is the commonly used abbreviation for the University of Iceland, the country’s leading public research university located in Reykjavík.
  • 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_69ca83d7a0388190ba1af89ed7ba36f9 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cc960a2760819084aab611eb1c43a9 completed April 1, 2026, 3:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69cffe30093481908b3ec394cf585642 completed April 3, 2026, 5:51 p.m.
NEDg Description generation batch_69d000d5b24481908679dbb92372c4b9 completed April 3, 2026, 6:03 p.m.
NED2 Entity disambiguation (via description) batch_69d001692c3481909924615717e316c2 completed April 3, 2026, 6:05 p.m.
Created at: March 30, 2026, 7:13 p.m.