Triple

T1292907
Position Surface form Disambiguated ID Type / Status
Subject Antonio B. Won Pat International Airport E27587 entity
Predicate ICAOcode P419 FINISHED
Object PGUM
PGUM is the ICAO airport code for Antonio B. Won Pat International Airport, the primary commercial airport serving Guam.
 E147283 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: PGUM | Statement: [Antonio B. Won Pat International Airport, ICAOcode, PGUM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PGUM
Context triple: [Antonio B. Won Pat International Airport, ICAOcode, PGUM]
  • A. PUM
    PUM is the stock ticker symbol for Puma, the German multinational sportswear and athletic footwear company.
  • B. PEG
    PEG is the stock ticker symbol for Public Service Enterprise Group, a major U.S. energy company primarily involved in regulated electric and gas utility operations and power generation.
  • C. GRPM
    GRPM is a regional museum in Grand Rapids, Michigan, known for its exhibits on local history, science, and culture.
  • D. PGS
    PGS stands for Prompt Global Strike, a U.S. military concept aimed at enabling rapid, precision conventional strikes anywhere in the world within a short time frame.
  • E. PAPPG
    PAPPG is the National Science Foundation’s comprehensive guide outlining the policies, procedures, and requirements for preparing and managing NSF grant proposals and awards.
  • 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: PGUM
Triple: [Antonio B. Won Pat International Airport, ICAOcode, PGUM]
Generated description
PGUM is the ICAO airport code for Antonio B. Won Pat International Airport, the primary commercial airport serving Guam.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PGUM
Target entity description: PGUM is the ICAO airport code for Antonio B. Won Pat International Airport, the primary commercial airport serving Guam.
  • A. PUM
    PUM is the stock ticker symbol for Puma, the German multinational sportswear and athletic footwear company.
  • B. PEG
    PEG is the stock ticker symbol for Public Service Enterprise Group, a major U.S. energy company primarily involved in regulated electric and gas utility operations and power generation.
  • C. GRPM
    GRPM is a regional museum in Grand Rapids, Michigan, known for its exhibits on local history, science, and culture.
  • D. PGS
    PGS stands for Prompt Global Strike, a U.S. military concept aimed at enabling rapid, precision conventional strikes anywhere in the world within a short time frame.
  • E. PAPPG
    PAPPG is the National Science Foundation’s comprehensive guide outlining the policies, procedures, and requirements for preparing and managing NSF grant proposals and awards.
  • 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_69a496d4ec448190ad653b2590c46711 completed March 1, 2026, 7:43 p.m.
NER Named-entity recognition batch_69a4c0f09d5c81909e6dc036fe9c5b4a completed March 1, 2026, 10:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69acacbf0cf48190937f620900b08d3f completed March 7, 2026, 10:54 p.m.
NEDg Description generation batch_69acad34fc008190a9c06be5cbe8e8c3 completed March 7, 2026, 10:56 p.m.
NED2 Entity disambiguation (via description) batch_69acadc3ceb48190a9d67c8e90034c49 completed March 7, 2026, 10:59 p.m.
Created at: March 1, 2026, 7:51 p.m.