Triple

T20225143
Position Surface form Disambiguated ID Type / Status
Subject Salgado Filho International Airport E495357 entity
Predicate ICAOcode P419 FINISHED
Object SBPA
SBPA is the ICAO airport code for Salgado Filho International Airport, the main airport serving Porto Alegre in southern Brazil.
 E1419450 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: SBPA | Statement: [Salgado Filho International Airport, ICAOcode, SBPA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SBPA
Context triple: [Salgado Filho International Airport, ICAOcode, SBPA]
  • A. SBPA
    SBPA is the acronym for the School of Business and Public Administration, an academic unit focused on education and research in business and public sector management.
  • B. BSAP
    BSAP is an environmental program aimed at restoring the ecological health of the Baltic Sea through coordinated actions by the surrounding countries.
  • C. SBP
    SBP is the National Rail station code for Stonebridge Park railway station in northwest London, England.
  • D. SBP
    SBP is a federally assisted meal program in the United States that provides nutritious breakfasts to schoolchildren to support their health and learning.
  • E. SBP
    SBP is the central bank of Pakistan, responsible for regulating the country’s monetary and credit system and ensuring financial stability.
  • 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: SBPA
Triple: [Salgado Filho International Airport, ICAOcode, SBPA]
Generated description
SBPA is the ICAO airport code for Salgado Filho International Airport, the main airport serving Porto Alegre in southern Brazil.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SBPA
Target entity description: SBPA is the ICAO airport code for Salgado Filho International Airport, the main airport serving Porto Alegre in southern Brazil.
  • A. SBPA
    SBPA is the acronym for the School of Business and Public Administration, an academic unit focused on education and research in business and public sector management.
  • B. BSAP
    BSAP is an environmental program aimed at restoring the ecological health of the Baltic Sea through coordinated actions by the surrounding countries.
  • C. SBP
    SBP is the National Rail station code for Stonebridge Park railway station in northwest London, England.
  • D. SBP
    SBP is the central bank of Pakistan, responsible for regulating the country’s monetary and credit system and ensuring financial stability.
  • E. SBP
    SBP is a federally assisted meal program in the United States that provides nutritious breakfasts to schoolchildren to support their health and learning.
  • 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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66fd8f1948190adbb947a7870bb43 completed April 20, 2026, 6:26 p.m.
NED1 Entity disambiguation (via context triple) batch_6a084b887c6081908fc79047cf4f73c6 completed May 16, 2026, 10:48 a.m.
NEDg Description generation batch_6a084c6561ec8190b1eee3d94aeb5009 completed May 16, 2026, 10:52 a.m.
NED2 Entity disambiguation (via description) batch_6a084d0ac2f881909be142d6b30cc9ec completed May 16, 2026, 10:55 a.m.
Created at: April 11, 2026, 11:39 p.m.