Triple

T18549507
Position Surface form Disambiguated ID Type / Status
Subject Manhattan Regional Airport E453333 entity
Predicate ICAOcode P419 FINISHED
Object KMHK
KMHK is the ICAO airport code for Manhattan Regional Airport, a public airport serving Manhattan, Kansas, in the United States.
 E1330633 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: KMHK | Statement: [Manhattan Regional Airport, ICAOcode, KMHK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KMHK
Context triple: [Manhattan Regional Airport, ICAOcode, KMHK]
  • A. MHK
    MHK is the post-nominal abbreviation used by elected members of the House of Keys, the lower branch of the Isle of Man's parliament.
  • B. KHC
    KHC is a selective interdisciplinary honors college at Boston University that offers an enriched curriculum and close-knit academic community for high-achieving undergraduates.
  • C. KHM
    KHM is the commonly used abbreviation for the Kunsthistorisches Museum, a major art and cultural history museum in Vienna, Austria.
  • D. KKH
    KKH is the abbreviation for the Karakoram Highway, a major high-altitude road linking Pakistan and China through the Karakoram mountain range.
  • E. KMH
    KMH is the Royal College of Music in Stockholm, a leading Swedish institution for higher education in music performance, composition, and pedagogy.
  • 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: KMHK
Triple: [Manhattan Regional Airport, ICAOcode, KMHK]
Generated description
KMHK is the ICAO airport code for Manhattan Regional Airport, a public airport serving Manhattan, Kansas, in the United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KMHK
Target entity description: KMHK is the ICAO airport code for Manhattan Regional Airport, a public airport serving Manhattan, Kansas, in the United States.
  • A. MHK
    MHK is the post-nominal abbreviation used by elected members of the House of Keys, the lower branch of the Isle of Man's parliament.
  • B. KHC
    KHC is a selective interdisciplinary honors college at Boston University that offers an enriched curriculum and close-knit academic community for high-achieving undergraduates.
  • C. KHM
    KHM is the commonly used abbreviation for the Kunsthistorisches Museum, a major art and cultural history museum in Vienna, Austria.
  • D. KKH
    KKH is the abbreviation for the Karakoram Highway, a major high-altitude road linking Pakistan and China through the Karakoram mountain range.
  • E. KMH
    KMH is the Royal College of Music in Stockholm, a leading Swedish institution for higher education in music performance, composition, and pedagogy.
  • 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_69d8d388b0c881908e610a1c45b52640 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e534beeb408190a03f6d7c3f2ef389 completed April 19, 2026, 8:02 p.m.
NED1 Entity disambiguation (via context triple) batch_6a049add8acc8190b00aeae2555ca593 completed May 13, 2026, 3:38 p.m.
NEDg Description generation batch_6a049bf32520819091b9deaba331f9ca completed May 13, 2026, 3:42 p.m.
NED2 Entity disambiguation (via description) batch_6a049ccb59108190870c11bd11949f3b completed May 13, 2026, 3:46 p.m.
Created at: April 10, 2026, 11:38 a.m.