Triple

T6894635
Position Surface form Disambiguated ID Type / Status
Subject Hangzhou Xiaoshan International Airport E159140 entity
Predicate IATAcode P418 FINISHED
Object HGH
HGH is the IATA airport code for Hangzhou Xiaoshan International Airport, the main international airport serving Hangzhou in eastern China.
 E626734 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: HGH | Statement: [Hangzhou Xiaoshan International Airport, IATAcode, HGH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HGH
Context triple: [Hangzhou Xiaoshan International Airport, IATAcode, HGH]
  • A. BGH
    BGH is the highest court of ordinary jurisdiction in Germany, responsible for final appeals in civil and criminal cases.
  • B. HGF
    HGF is the abbreviation for the Helmholtz Association, Germany’s largest scientific research organization spanning multiple disciplines and large-scale facilities.
  • C. HGF
    HGF is the National Rail station code for Hag Fold railway station in Greater Manchester, England.
  • D. LH
    The LH is a mid-1970s generation of the Holden Torana, an Australian compact car series known for its performance-oriented variants and motorsport success.
  • E. LH
    LH is the two-letter IATA airline designator used to identify Lufthansa flights in global aviation systems.
  • 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: HGH
Triple: [Hangzhou Xiaoshan International Airport, IATAcode, HGH]
Generated description
HGH is the IATA airport code for Hangzhou Xiaoshan International Airport, the main international airport serving Hangzhou in eastern China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HGH
Target entity description: HGH is the IATA airport code for Hangzhou Xiaoshan International Airport, the main international airport serving Hangzhou in eastern China.
  • A. BGH
    BGH is the highest court of ordinary jurisdiction in Germany, responsible for final appeals in civil and criminal cases.
  • B. HGF
    HGF is the abbreviation for the Helmholtz Association, Germany’s largest scientific research organization spanning multiple disciplines and large-scale facilities.
  • C. HGF
    HGF is the National Rail station code for Hag Fold railway station in Greater Manchester, England.
  • D. LH
    LH is the two-letter IATA airline designator used to identify Lufthansa flights in global aviation systems.
  • E. LH
    The LH is a mid-1970s generation of the Holden Torana, an Australian compact car series known for its performance-oriented variants and motorsport success.
  • 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_69c6883568c8819081db6407e892cccc completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d933032c8190997d67a15897619b completed March 27, 2026, 7:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c748db2bd48190bb26f60c58ec8229 completed March 28, 2026, 3:19 a.m.
NEDg Description generation batch_69c749901de081908e5c3ccd324e8191 completed March 28, 2026, 3:22 a.m.
NED2 Entity disambiguation (via description) batch_69c74a0bcddc819084b22925cf57a205 completed March 28, 2026, 3:24 a.m.
Created at: March 27, 2026, 2:24 p.m.