Triple

T6066242
Position Surface form Disambiguated ID Type / Status
Subject Pyongyang Sunan International Airport E135167 entity
Predicate hasICAOcode P419 FINISHED
Object ZKPY
ZKPY is the ICAO airport code for Pyongyang Sunan International Airport, the main international gateway to North Korea’s capital.
 E567243 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: ZKPY | Statement: [Pyongyang Sunan International Airport, hasICAOcode, ZKPY]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ZKPY
Context triple: [Pyongyang Sunan International Airport, hasICAOcode, ZKPY]
  • A. KZ
    KZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Kazakhstan for international standardization and identification.
  • B. KNZY
    KNZY is the ICAO airport code for Naval Air Station North Island, a major U.S. Navy aviation facility located in San Diego, California.
  • C. KZT
    KZT is the currency code for the Kazakhstani tenge, the official monetary unit of Kazakhstan.
  • D. PZ
    PZ is the IATA airline designator assigned to LATAM Airlines Paraguay, the Paraguayan branch of the LATAM Airlines Group.
  • E. PZ
    PZ is the vehicle registration code used on license plates for vehicles registered in the Preveza regional unit of Greece.
  • 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: ZKPY
Triple: [Pyongyang Sunan International Airport, hasICAOcode, ZKPY]
Generated description
ZKPY is the ICAO airport code for Pyongyang Sunan International Airport, the main international gateway to North Korea’s capital.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ZKPY
Target entity description: ZKPY is the ICAO airport code for Pyongyang Sunan International Airport, the main international gateway to North Korea’s capital.
  • A. KZ
    KZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Kazakhstan for international standardization and identification.
  • B. KNZY
    KNZY is the ICAO airport code for Naval Air Station North Island, a major U.S. Navy aviation facility located in San Diego, California.
  • C. KZT
    KZT is the currency code for the Kazakhstani tenge, the official monetary unit of Kazakhstan.
  • D. PZ
    PZ is the IATA airline designator assigned to LATAM Airlines Paraguay, the Paraguayan branch of the LATAM Airlines Group.
  • E. PZ
    PZ is the vehicle registration code used on license plates for vehicles registered in the Preveza regional unit of Greece.
  • 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_69c00878d06881909ee78e88913bf890 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c0573df7508190bbb5b496188b2f3e completed March 22, 2026, 8:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69c11d23dca8819080702ca0f05df5dd completed March 23, 2026, 10:59 a.m.
NEDg Description generation batch_69c11dec348c819090715aa1ec407f11 completed March 23, 2026, 11:03 a.m.
NED2 Entity disambiguation (via description) batch_69c11e5efd848190adb834e42b4bdc9e completed March 23, 2026, 11:05 a.m.
Created at: March 22, 2026, 4:10 p.m.