Triple

T7865081
Position Surface form Disambiguated ID Type / Status
Subject Kigoma Airport E182595 entity
Predicate IATAcode P418 FINISHED
Object TKQ
TKQ is the IATA airport code for Kigoma Airport in western Tanzania, serving the town of Kigoma on Lake Tanganyika.
 E700984 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: TKQ | Statement: [Kigoma Airport, IATAcode, TKQ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: TKQ
Context triple: [Kigoma Airport, IATAcode, TKQ]
  • A. TQG
    "TQG" is a 2023 reggaeton-pop collaboration between Shakira and Karol G known for its themes of empowerment and post-breakup resilience.
  • B. TK
    TK is the two-letter IATA airline designator used to identify Turkish Airlines in global aviation systems.
  • C. QK
    QK is the former IATA airline designator once assigned to Eastern Provincial Airways, a regional carrier in Canada.
  • D. TKF
    TKF is the IATA airport code for Truckee Tahoe Airport, a general aviation airport serving the Truckee and Lake Tahoe region in California, USA.
  • E. TKO
    TKO is the stock ticker symbol for TKO Group Holdings, the publicly traded parent company formed by the merger of WWE and UFC under Endeavor.
  • 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: TKQ
Triple: [Kigoma Airport, IATAcode, TKQ]
Generated description
TKQ is the IATA airport code for Kigoma Airport in western Tanzania, serving the town of Kigoma on Lake Tanganyika.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: TKQ
Target entity description: TKQ is the IATA airport code for Kigoma Airport in western Tanzania, serving the town of Kigoma on Lake Tanganyika.
  • A. TQG
    "TQG" is a 2023 reggaeton-pop collaboration between Shakira and Karol G known for its themes of empowerment and post-breakup resilience.
  • B. TK
    TK is the two-letter IATA airline designator used to identify Turkish Airlines in global aviation systems.
  • C. QK
    QK is the former IATA airline designator once assigned to Eastern Provincial Airways, a regional carrier in Canada.
  • D. TKF
    TKF is the IATA airport code for Truckee Tahoe Airport, a general aviation airport serving the Truckee and Lake Tahoe region in California, USA.
  • E. TKO
    TKO is the stock ticker symbol for TKO Group Holdings, the publicly traded parent company formed by the merger of WWE and UFC under Endeavor.
  • 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_69ca82894d9081908a832bfce71a4714 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb36c0eaa48190a0df4c37c726546e completed March 31, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5b51c01481909c34a8d0efb89577 completed March 31, 2026, 5:27 a.m.
NEDg Description generation batch_69cb762fda2c81908ed508e12cabb938 completed March 31, 2026, 7:22 a.m.
NED2 Entity disambiguation (via description) batch_69cbbf706e888190bfd08d9d78945c49 completed March 31, 2026, 12:34 p.m.
Created at: March 30, 2026, 4:54 p.m.