Triple

T5323979
Position Surface form Disambiguated ID Type / Status
Subject School Breakfast Program E121742 entity
Predicate acronym P43 FINISHED
Object SBP
SBP is a federally assisted meal program in the United States that provides nutritious breakfasts to schoolchildren to support their health and learning.
 E512069 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: SBP | Statement: [School Breakfast Program, acronym, SBP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SBP
Context triple: [School Breakfast Program, acronym, SBP]
  • A. SBSP
    SBSP is the ICAO airport code for Congonhas–São Paulo Airport, a major domestic airport serving the city of São Paulo, Brazil.
  • B. SB
    SB was the communist-era secret police and intelligence service of the Polish People's Republic, known for surveillance, repression, and political control.
  • C. SB
    SB is the vehicle registration code used on license plates for cars registered in the city of Bielsko-Biała in southern Poland.
  • D. SP
    SP is the official aircraft registration prefix used to identify airplanes registered in Poland.
  • E. SP
    SP is the commonly used abbreviation for the Social Democratic Party of Switzerland, a major center-left political party in the country.
  • 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: SBP
Triple: [School Breakfast Program, acronym, SBP]
Generated description
SBP is a federally assisted meal program in the United States that provides nutritious breakfasts to schoolchildren to support their health and learning.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SBP
Target entity description: SBP is a federally assisted meal program in the United States that provides nutritious breakfasts to schoolchildren to support their health and learning.
  • A. SBSP
    SBSP is the ICAO airport code for Congonhas–São Paulo Airport, a major domestic airport serving the city of São Paulo, Brazil.
  • B. SB
    SB was the communist-era secret police and intelligence service of the Polish People's Republic, known for surveillance, repression, and political control.
  • C. SB
    SB is the vehicle registration code used on license plates for cars registered in the city of Bielsko-Biała in southern Poland.
  • D. SP
    SP is the official aircraft registration prefix used to identify airplanes registered in Poland.
  • E. SP
    SP is the commonly used abbreviation for the Social Democratic Party of Switzerland, a major center-left political party in the country.
  • 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_69bd463d956c819088105c3db802c017 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd8579b3e88190a1d21d4b74169617 completed March 20, 2026, 5:35 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf18a836988190b7baf3c24fea6f03 completed March 21, 2026, 10:16 p.m.
NEDg Description generation batch_69bf19c8273081908a5138e9af921ec7 completed March 21, 2026, 10:20 p.m.
NED2 Entity disambiguation (via description) batch_69bf1a3049648190b5040e587671610a completed March 21, 2026, 10:22 p.m.
Created at: March 20, 2026, 1:59 p.m.