Triple

T14947446
Position Surface form Disambiguated ID Type / Status
Subject Kinston Regional Jetport E372701 entity
Predicate icaoCode P419 FINISHED
Object KISO
KISO is the ICAO airport code for Kinston Regional Jetport, a public airport serving Kinston, North Carolina.
E1128217 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: KISO | Statement: [Kinston Regional Jetport, icaoCode, KISO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KISO
Context triple: [Kinston Regional Jetport, icaoCode, KISO]
  • A. Kiso
    Kiso is a town in Nagano Prefecture, Japan, known for its scenic Kiso Valley, traditional post towns on the old Nakasendō route, and proximity to Mount Ontake.
  • B. KISA
    KISA is the Korea Internet & Security Agency, a government-affiliated organization that manages South Korea’s internet infrastructure and cybersecurity, including administration of the .kr country-code top-level domain.
  • C. KIS
    KIS is the IATA airport code for Kisumu International Airport, a key air transport hub serving the city of Kisumu in western Kenya.
  • D. kiso1238
    kiso1238 is the Glottolog code for Kisolongo, a Bantu language variety documented in linguistic classification databases.
  • E. Kiesen
    Kiesen is a municipality in the canton of Bern, Switzerland, served by a station on the Bern–Thun railway line.
  • 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: KISO
Triple: [Kinston Regional Jetport, icaoCode, KISO]
Generated description
KISO is the ICAO airport code for Kinston Regional Jetport, a public airport serving Kinston, North Carolina.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: KISO
Target entity description: KISO is the ICAO airport code for Kinston Regional Jetport, a public airport serving Kinston, North Carolina.
  • A. Kiso
    Kiso is a town in Nagano Prefecture, Japan, known for its scenic Kiso Valley, traditional post towns on the old Nakasendō route, and proximity to Mount Ontake.
  • B. KISA
    KISA is the Korea Internet & Security Agency, a government-affiliated organization that manages South Korea’s internet infrastructure and cybersecurity, including administration of the .kr country-code top-level domain.
  • C. KIS
    KIS is the IATA airport code for Kisumu International Airport, a key air transport hub serving the city of Kisumu in western Kenya.
  • D. kiso1238
    kiso1238 is the Glottolog code for Kisolongo, a Bantu language variety documented in linguistic classification databases.
  • E. Kiesen
    Kiesen is a municipality in the canton of Bern, Switzerland, served by a station on the Bern–Thun railway line.
  • 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_69d85cca979481908747d2a81eba1cea completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded68e35c481908e47cd68441c5115 completed April 15, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe7e963c548190b3a06ffbbb3298b2 completed May 9, 2026, 12:23 a.m.
NEDg Description generation batch_69fe807eaa208190a478f0d0599ef695 completed May 9, 2026, 12:31 a.m.
NED2 Entity disambiguation (via description) batch_69fe811c14448190b85d94244adcd662 completed May 9, 2026, 12:34 a.m.
Created at: April 10, 2026, 2:39 a.m.