Triple

T10852912
Position Surface form Disambiguated ID Type / Status
Subject Florida Board of Governors E256192 entity
Predicate shortName P43 FINISHED
Object BOG
BOG is the commonly used acronym for the Florida Board of Governors, the governing body overseeing the State University System of Florida.
E889785 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: BOG | Statement: [Florida Board of Governors, shortName, BOG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BOG
Context triple: [Florida Board of Governors, shortName, BOG]
  • A. BOG
    BOG is the vehicle registration code used for motor vehicles registered in the Capital District of Bogotá, Colombia.
  • B. BOG
    BOG is the IATA airport code for El Dorado International Airport, the main international gateway serving Bogotá, Colombia.
  • C. BOH
    BOH is the three-letter IATA airport code for Bournemouth Airport in southern England.
  • D. BO
    BO is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Bolivia in international standards and systems.
  • E. BOL
    BOL is the three-letter ISO 3166-1 alpha-3 country code assigned to Bolivia.
  • 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: BOG
Triple: [Florida Board of Governors, shortName, BOG]
Generated description
BOG is the commonly used acronym for the Florida Board of Governors, the governing body overseeing the State University System of Florida.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: BOG
Target entity description: BOG is the commonly used acronym for the Florida Board of Governors, the governing body overseeing the State University System of Florida.
  • A. BOG
    BOG is the IATA airport code for El Dorado International Airport, the main international gateway serving Bogotá, Colombia.
  • B. BOG
    BOG is the vehicle registration code used for motor vehicles registered in the Capital District of Bogotá, Colombia.
  • C. BOH
    BOH is the three-letter IATA airport code for Bournemouth Airport in southern England.
  • D. BO
    BO is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Bolivia in international standards and systems.
  • E. BOL
    BOL is the three-letter ISO 3166-1 alpha-3 country code assigned to Bolivia.
  • 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_69d6aa83d1448190a66d93c32394d21f completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d75134299481909459fd87917261a7 completed April 9, 2026, 7:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb18a48248190999f95abc979fa74 completed April 14, 2026, 9:28 p.m.
NEDg Description generation batch_69ded06ea3c08190a9a9fc5fde2fd62d completed April 14, 2026, 11:40 p.m.
NED2 Entity disambiguation (via description) batch_69ded43b8ca48190b49f6edf2f46870f completed April 14, 2026, 11:56 p.m.
Created at: April 8, 2026, 9:20 p.m.