Triple

T2675474
Position Surface form Disambiguated ID Type / Status
Subject Beechcraft C-45 Expeditor E56447 entity
Predicate notableVariant P4680 FINISHED
Object SNB
SNB is the U.S. Navy’s military transport and trainer variant of the Beechcraft Model 18 aircraft.
 E287099 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: SNB | Statement: [Beechcraft C-45 Expeditor, notableVariant, SNB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SNB
Context triple: [Beechcraft C-45 Expeditor, notableVariant, SNB]
  • A. SNB
    SNB is the central bank of Switzerland responsible for the country’s monetary policy and the stability of the Swiss financial system.
  • B. NSB
    NSB is the acronym for the National Science Board, the governing body that advises the U.S. government on national science and engineering policy and oversees the National Science Foundation.
  • C. SN
    SN is the commonly used abbreviated form of the Ukrainian political party and former television series "Servant of the People."
  • D. SN
    SN is the IATA airline designator used to identify Brussels Airlines in global aviation systems.
  • E. GNB
    GNB is the commonly used abbreviation for the Good News Bible, a modern English translation of the Christian Bible known for its clear and simple language.
  • 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: SNB
Triple: [Beechcraft C-45 Expeditor, notableVariant, SNB]
Generated description
SNB is the U.S. Navy’s military transport and trainer variant of the Beechcraft Model 18 aircraft.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SNB
Target entity description: SNB is the U.S. Navy’s military transport and trainer variant of the Beechcraft Model 18 aircraft.
  • A. SNB
    SNB is the central bank of Switzerland responsible for the country’s monetary policy and the stability of the Swiss financial system.
  • B. NSB
    NSB is the acronym for the National Science Board, the governing body that advises the U.S. government on national science and engineering policy and oversees the National Science Foundation.
  • C. SN
    SN is the commonly used abbreviated form of the Ukrainian political party and former television series "Servant of the People."
  • D. SN
    SN is the IATA airline designator used to identify Brussels Airlines in global aviation systems.
  • E. GNB
    GNB is the commonly used abbreviation for the Good News Bible, a modern English translation of the Christian Bible known for its clear and simple language.
  • 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_69ab4a4b13fc81909dfdb3f23da46832 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd9b3530c819093942cc985f814ef completed March 7, 2026, 7:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69afa0638a9c8190b48ca5aa56eb66ff completed March 10, 2026, 4:38 a.m.
NEDg Description generation batch_69afa0e714e08190aa873b8501c89479 completed March 10, 2026, 4:41 a.m.
NED2 Entity disambiguation (via description) batch_69afa18335548190b186323227d55e63 completed March 10, 2026, 4:43 a.m.
Created at: March 6, 2026, 9:54 p.m.