Triple

T17498650
Position Surface form Disambiguated ID Type / Status
Subject Skagway Airport E426137 entity
Predicate ICAOCode P419 FINISHED
Object PAGY
PAGY is the ICAO airport code assigned to Skagway Airport in Skagway, Alaska.
E1272089 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: PAGY | Statement: [Skagway Airport, ICAOCode, PAGY]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PAGY
Context triple: [Skagway Airport, ICAOCode, PAGY]
  • A. Pagasae
    Pagasae was an ancient coastal city and harbor in Thessaly, Greece, known as a key port on the Pagasetic Gulf in classical antiquity.
  • B. Paguemen
    Paguemen is an alternative transliteration of the name Pagumen, which refers to the thirteenth month in the Ethiopian calendar.
  • C. Polygyros
    Polygyros is a town in northern Greece that serves as the capital of the Chalkidiki regional unit in Central Macedonia.
  • D. Papariga
    Papariga is a Greek surname most prominently associated with Aleka Papariga, a longtime leader of the Communist Party of Greece.
  • E. Supayalat
    Supayalat was the last queen of Burma, known for her political influence and role during the final years of the Konbaung dynasty before British annexation.
  • 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: PAGY
Triple: [Skagway Airport, ICAOCode, PAGY]
Generated description
PAGY is the ICAO airport code assigned to Skagway Airport in Skagway, Alaska.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: PAGY
Target entity description: PAGY is the ICAO airport code assigned to Skagway Airport in Skagway, Alaska.
  • A. Pagasae
    Pagasae was an ancient coastal city and harbor in Thessaly, Greece, known as a key port on the Pagasetic Gulf in classical antiquity.
  • B. Paguemen
    Paguemen is an alternative transliteration of the name Pagumen, which refers to the thirteenth month in the Ethiopian calendar.
  • C. Polygyros
    Polygyros is a town in northern Greece that serves as the capital of the Chalkidiki regional unit in Central Macedonia.
  • D. Papariga
    Papariga is a Greek surname most prominently associated with Aleka Papariga, a longtime leader of the Communist Party of Greece.
  • E. Supayalat
    Supayalat was the last queen of Burma, known for her political influence and role during the final years of the Konbaung dynasty before British annexation.
  • 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_69d889dccf7481909264a1844a2e9100 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4521028048190aa7c4023a72a12f4 completed April 19, 2026, 3:54 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01c2067774819089728021aef5f967 completed May 11, 2026, 11:48 a.m.
NEDg Description generation batch_6a01c36b06dc81909f52cbe1c57eb128 completed May 11, 2026, 11:54 a.m.
NED2 Entity disambiguation (via description) batch_6a01c41c4ce88190a7487661f10f40b5 completed May 11, 2026, 11:57 a.m.
Created at: April 10, 2026, 5:48 a.m.