Triple

T1365618
Position Surface form Disambiguated ID Type / Status
Subject Kobe Airport E29195 entity
Predicate IATAcode P418 FINISHED
Object UKB
UKB is the IATA airport code for Kobe Airport, a regional airport serving the city of Kobe in Japan.
E156537 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: UKB | Statement: [Kobe Airport, IATAcode, UKB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: UKB
Context triple: [Kobe Airport, IATAcode, UKB]
  • A. UKX
    UKX is the stock market index code used to represent the FTSE 100, a benchmark index of the largest companies listed on the London Stock Exchange.
  • B. NKGB
    NKGB was a Soviet state security and intelligence agency that operated before the formation of the KGB, handling internal security, counterintelligence, and secret police functions.
  • C. SK
    SK is the postcode area covering Stockport and surrounding parts of Greater Manchester and nearby counties in North West England.
  • D. BK
    BK is a common abbreviation for Brooklyn, a borough of New York City known for its cultural diversity, arts scene, and historic neighborhoods.
  • E. Usk
    Usk is a small historic town in Monmouthshire, southeast Wales, known for its medieval castle and picturesque setting on the River Usk.
  • 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: UKB
Triple: [Kobe Airport, IATAcode, UKB]
Generated description
UKB is the IATA airport code for Kobe Airport, a regional airport serving the city of Kobe in Japan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: UKB
Target entity description: UKB is the IATA airport code for Kobe Airport, a regional airport serving the city of Kobe in Japan.
  • A. UKX
    UKX is the stock market index code used to represent the FTSE 100, a benchmark index of the largest companies listed on the London Stock Exchange.
  • B. NKGB
    NKGB was a Soviet state security and intelligence agency that operated before the formation of the KGB, handling internal security, counterintelligence, and secret police functions.
  • C. SK
    SK is the postcode area covering Stockport and surrounding parts of Greater Manchester and nearby counties in North West England.
  • D. BK
    BK is a common abbreviation for Brooklyn, a borough of New York City known for its cultural diversity, arts scene, and historic neighborhoods.
  • E. Usk
    Usk is a small historic town in Monmouthshire, southeast Wales, known for its medieval castle and picturesque setting on the River Usk.
  • 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_69a498d77abc8190913bf57e5f51d2c4 completed March 1, 2026, 7:51 p.m.
NER Named-entity recognition batch_69a4c2d1d15481909d58b6fd8aa2e585 completed March 1, 2026, 10:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69acce7604908190a3754a20bdcb6266 completed March 8, 2026, 1:18 a.m.
NEDg Description generation batch_69accff65bf481908227d3837412276b completed March 8, 2026, 1:25 a.m.
NED2 Entity disambiguation (via description) batch_69acd0603f608190b37fad8f97f84f48 completed March 8, 2026, 1:26 a.m.
Created at: March 1, 2026, 7:57 p.m.