Triple

T7217858
Position Surface form Disambiguated ID Type / Status
Subject Keimyung University E150180 entity
Predicate shortName P43 FINISHED
Object KMU
KMU is the abbreviation commonly used for Keimyung University, a private Christian university located in Daegu, South Korea.
E649955 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: KMU | Statement: [Keimyung University, shortName, KMU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KMU
Context triple: [Keimyung University, shortName, KMU]
  • A. KSMF
    KSMF is the ICAO airport code for Sacramento International Airport, a major commercial airport serving California’s capital region.
  • B. KMLU
    KMLU is the ICAO airport code for Monroe Regional Airport, a public airport serving Monroe, Louisiana, in the United States.
  • C. KMCI
    KMCI is the ICAO code for Kansas City International Airport, a major commercial airport serving the Kansas City metropolitan area in Missouri, USA.
  • D. KRCU
    KRCU is a public radio station affiliated with Southeast Missouri State University that provides news, music, and cultural programming to the surrounding region.
  • E. KCSM
    KCSM is the Mexican subsidiary of the Kansas City Southern railway company, operating freight rail services across key industrial and cross-border corridors in Mexico.
  • 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: KMU
Triple: [Keimyung University, shortName, KMU]
Generated description
KMU is the abbreviation commonly used for Keimyung University, a private Christian university located in Daegu, South Korea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: KMU
Target entity description: KMU is the abbreviation commonly used for Keimyung University, a private Christian university located in Daegu, South Korea.
  • A. KSMF
    KSMF is the ICAO airport code for Sacramento International Airport, a major commercial airport serving California’s capital region.
  • B. KMLU
    KMLU is the ICAO airport code for Monroe Regional Airport, a public airport serving Monroe, Louisiana, in the United States.
  • C. KMCI
    KMCI is the ICAO code for Kansas City International Airport, a major commercial airport serving the Kansas City metropolitan area in Missouri, USA.
  • D. KRCU
    KRCU is a public radio station affiliated with Southeast Missouri State University that provides news, music, and cultural programming to the surrounding region.
  • E. KCSM
    KCSM is the Mexican subsidiary of the Kansas City Southern railway company, operating freight rail services across key industrial and cross-border corridors in Mexico.
  • 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_69c687effb44819092b95d07d0368c9f completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6e99170d88190b1aef326a7d81134 completed March 27, 2026, 8:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7cbfb46388190992cc98039e71748 completed March 28, 2026, 12:39 p.m.
NEDg Description generation batch_69c7cce6a290819096ff68333cd3a3cf completed March 28, 2026, 12:43 p.m.
NED2 Entity disambiguation (via description) batch_69c7cd9966e481909eb3c23bb59777d9 completed March 28, 2026, 12:46 p.m.
Created at: March 27, 2026, 2:53 p.m.