Triple

T22703224
Position Surface form Disambiguated ID Type / Status
Subject Kyung Hee University E561377 entity
Predicate shortName P43 FINISHED
Object KHU
KHU is a major private research university in South Korea known for its comprehensive academic programs and strong emphasis on internationalization.
 E1550124 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: KHU | Statement: [Kyung Hee University, shortName, KHU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KHU
Context triple: [Kyung Hee University, shortName, KHU]
  • A. KHAE
    KHAE is the ICAO airport code for Hannibal Regional Airport, a public-use airport serving the Hannibal, Missouri area in the United States.
  • B. KHWO
    KHWO is the ICAO airport code for North Perry Airport, a general aviation facility located in Pembroke Pines, Florida, United States.
  • C. KHIB
    KHIB is the ICAO airport code for Range Regional Airport in Hibbing, Minnesota, United States.
  • D. KH
    KH is the German vehicle registration code assigned to the district centered around the town of Bad Kreuznach in Rhineland-Palatinate.
  • E. KH
    KH is the station code for Copenhagen Central Station, the main railway hub in Denmark’s capital city.
  • 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: KHU
Triple: [Kyung Hee University, shortName, KHU]
Generated description
KHU is a major private research university in South Korea known for its comprehensive academic programs and strong emphasis on internationalization.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KHU
Target entity description: KHU is a major private research university in South Korea known for its comprehensive academic programs and strong emphasis on internationalization.
  • A. KHAE
    KHAE is the ICAO airport code for Hannibal Regional Airport, a public-use airport serving the Hannibal, Missouri area in the United States.
  • B. KHWO
    KHWO is the ICAO airport code for North Perry Airport, a general aviation facility located in Pembroke Pines, Florida, United States.
  • C. KHIB
    KHIB is the ICAO airport code for Range Regional Airport in Hibbing, Minnesota, United States.
  • D. KH
    KH is the German vehicle registration code assigned to the district centered around the town of Bad Kreuznach in Rhineland-Palatinate.
  • E. KH
    KH is the station code for Copenhagen Central Station, the main railway hub in Denmark’s capital city.
  • 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_69e2454e615481909c177440be559d2c completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f178cbf5788190bc8cd1bc71a861e5 completed April 29, 2026, 3:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b7ed40b5c8190a2ac99d215de0c31 completed May 18, 2026, 9:04 p.m.
NEDg Description generation batch_6a0b7f9ccb00819092fe5e9d71f545e4 completed May 18, 2026, 9:07 p.m.
NED2 Entity disambiguation (via description) batch_6a0b806b4e1481909babc97a8914947a completed May 18, 2026, 9:11 p.m.
Created at: April 17, 2026, 3:16 p.m.