Triple

T9501320
Position Surface form Disambiguated ID Type / Status
Subject Roshchino International Airport E229146 entity
Predicate IATAcode P418 FINISHED
Object TJM
TJM is the IATA airport code for Roshchino International Airport serving Tyumen in western Siberia, Russia.
 E803559 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: TJM | Statement: [Roshchino International Airport, IATAcode, TJM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: TJM
Context triple: [Roshchino International Airport, IATAcode, TJM]
  • A. tj
    tj is the GitHub username of TJ Holowaychuk, a prolific open-source developer known for creating popular Node.js and Go tools and frameworks.
  • B. TJT
    TJT is the time zone used in Tajikistan, corresponding to Tajikistan Time (UTC+5).
  • C. JT
    JT is a lightweight 3D visualization and data exchange file format commonly used in CAD and PLM workflows for efficient sharing of complex product models.
  • D. JT
    JT is a 1977 studio album by American singer-songwriter James Taylor that marked his commercial resurgence with hits like "Handy Man" and "Your Smiling Face."
  • E. ZTM
    ZTM is a notable work created by Z-Money, likely recognized as one of the artist's key music releases.
  • 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: TJM
Triple: [Roshchino International Airport, IATAcode, TJM]
Generated description
TJM is the IATA airport code for Roshchino International Airport serving Tyumen in western Siberia, Russia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: TJM
Target entity description: TJM is the IATA airport code for Roshchino International Airport serving Tyumen in western Siberia, Russia.
  • A. tj
    tj is the GitHub username of TJ Holowaychuk, a prolific open-source developer known for creating popular Node.js and Go tools and frameworks.
  • B. TJT
    TJT is the time zone used in Tajikistan, corresponding to Tajikistan Time (UTC+5).
  • C. JT
    JT is a lightweight 3D visualization and data exchange file format commonly used in CAD and PLM workflows for efficient sharing of complex product models.
  • D. JT
    JT is a 1977 studio album by American singer-songwriter James Taylor that marked his commercial resurgence with hits like "Handy Man" and "Your Smiling Face."
  • E. ZTM
    ZTM is a notable work created by Z-Money, likely recognized as one of the artist's key music releases.
  • 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_69ca84753660819098e8d416e89e26ae completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd983d4b708190a4dfef1246986a26 completed April 1, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69d13a10f7b08190b8e4d4bc3b9815c6 completed April 4, 2026, 4:19 p.m.
NEDg Description generation batch_69d13af4a2d481908dbec71fa8c25c69 completed April 4, 2026, 4:23 p.m.
NED2 Entity disambiguation (via description) batch_69d13bb706a88190bc2eec00c3e52e94 completed April 4, 2026, 4:26 p.m.
Created at: March 30, 2026, 7:57 p.m.