Triple

T530899
Position Surface form Disambiguated ID Type / Status
Subject Beijing Capital International Airport E12219 entity
Predicate IATAcode P418 FINISHED
Object PEK
PEK is the IATA airport code for Beijing Capital International Airport, one of the busiest and largest aviation hubs in China and the world.
 E66112 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: PEK | Statement: [Beijing Capital International Airport, IATAcode, PEK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PEK
Context triple: [Beijing Capital International Airport, IATAcode, PEK]
  • A. PK
    PK is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Pakistan in international standards and systems.
  • B. Pyongyang
    Pyongyang is the capital and largest city of North Korea, serving as its political, economic, and cultural center.
  • C. Kota
    Kota is a major industrial and educational city in southeastern Rajasthan, India, known for its coaching institutes and power plants along the Chambal River.
  • D. Penge
    Penge is a suburban district in southeast London known for its Victorian architecture and proximity to Crystal Palace.
  • E. Pkhali
    Pkhali is a traditional Georgian dish of finely chopped vegetables or greens mixed with ground walnuts, garlic, herbs, and spices, often served as a cold appetizer.
  • 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: PEK
Triple: [Beijing Capital International Airport, IATAcode, PEK]
Generated description
PEK is the IATA airport code for Beijing Capital International Airport, one of the busiest and largest aviation hubs in China and the world.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PEK
Target entity description: PEK is the IATA airport code for Beijing Capital International Airport, one of the busiest and largest aviation hubs in China and the world.
  • A. PK
    PK is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Pakistan in international standards and systems.
  • B. Pyongyang
    Pyongyang is the capital and largest city of North Korea, serving as its political, economic, and cultural center.
  • C. Kota
    Kota is a major industrial and educational city in southeastern Rajasthan, India, known for its coaching institutes and power plants along the Chambal River.
  • D. Penge
    Penge is a suburban district in southeast London known for its Victorian architecture and proximity to Crystal Palace.
  • E. Pkhali
    Pkhali is a traditional Georgian dish of finely chopped vegetables or greens mixed with ground walnuts, garlic, herbs, and spices, often served as a cold appetizer.
  • 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_69a4933208e88190891f5debab1b776d completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a494dda58c8190870305056838a2b2 completed March 1, 2026, 7:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4b5dabbe88190acf66bd30bc6312d completed March 1, 2026, 9:55 p.m.
NEDg Description generation batch_69a4b64487bc8190b879ddedc1585a04 completed March 1, 2026, 9:57 p.m.
NED2 Entity disambiguation (via description) batch_69a4b6ca3398819094bfbac0ba7a9c66 completed March 1, 2026, 9:59 p.m.
Created at: March 1, 2026, 7:32 p.m.