Triple

T22483379
Position Surface form Disambiguated ID Type / Status
Subject Summerside Airport E555821 entity
Predicate hasIATACode P2569 FINISHED
Object YSU
YSU is the IATA airport code for Summerside Airport in Prince Edward Island, Canada.
 E1539483 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: YSU | Statement: [Summerside Airport, hasIATACode, YSU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: YSU
Context triple: [Summerside Airport, hasIATACode, YSU]
  • A. YSU
    YSU is a public research university located in Youngstown, Ohio, known for its diverse academic programs and strong regional presence.
  • B. YSU
    YSU is the commonly used abbreviation for Yerevan State University, a major public research university in Armenia.
  • C. YBSU
    YBSU is the ICAO airport code for Sunshine Coast Airport in Queensland, Australia.
  • D. TSU
    TSU is the commonly used abbreviation for Tennessee State University's athletic teams, particularly its NCAA Division I FCS football program, the Tennessee State Tigers.
  • E. TSU
    TSU is the Titan Student Union, a central hub on the California State University, Fullerton campus that provides student services, event spaces, and social gathering areas.
  • 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: YSU
Triple: [Summerside Airport, hasIATACode, YSU]
Generated description
YSU is the IATA airport code for Summerside Airport in Prince Edward Island, Canada.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: YSU
Target entity description: YSU is the IATA airport code for Summerside Airport in Prince Edward Island, Canada.
  • A. YSU
    YSU is a public research university located in Youngstown, Ohio, known for its diverse academic programs and strong regional presence.
  • B. YSU
    YSU is the commonly used abbreviation for Yerevan State University, a major public research university in Armenia.
  • C. YBSU
    YBSU is the ICAO airport code for Sunshine Coast Airport in Queensland, Australia.
  • D. TSU
    TSU is the commonly used abbreviation for Tennessee State University's athletic teams, particularly its NCAA Division I FCS football program, the Tennessee State Tigers.
  • E. TSU
    TSU is the commonly used abbreviation for Ivane Javakhishvili Tbilisi State University, a major public research university in Tbilisi, Georgia.
  • 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_69e11e53897c819088863779f8c50bb0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15c3b03d881909e286a124c1a2b1c completed April 29, 2026, 1:17 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b12645b2c819080826a02b6151429 completed May 18, 2026, 1:21 p.m.
NEDg Description generation batch_6a0b14b7acac819090bfd6144df84be6 completed May 18, 2026, 1:31 p.m.
NED2 Entity disambiguation (via description) batch_6a0b154f7e0c8190b0ca64d582982d62 completed May 18, 2026, 1:34 p.m.
Created at: April 16, 2026, 8:49 p.m.