Triple

T18580547
Position Surface form Disambiguated ID Type / Status
Subject Southbury railway station E454100 entity
Predicate railcode P27071 FINISHED
Object SBU
SBU is the three-letter station code used to identify Southbury railway station in the UK rail network.
 E1331818 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: SBU | Statement: [Southbury railway station, railcode, SBU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SBU
Context triple: [Southbury railway station, railcode, SBU]
  • A. SBU
    SBU is a major public research university in Tehran, Iran, known for its strong programs in engineering, humanities, and social sciences.
  • B. SBU
    SBU is the abbreviation for the Special Boarding Unit, an elite maritime special operations force of the Indian Navy.
  • C. SBU
    SBU is a major public research university located on Long Island, New York, known for its strong science, engineering, and medical programs.
  • D. SBU
    SBU is the main domestic security and intelligence agency of Ukraine, responsible for counterintelligence, counterterrorism, and protecting state secrets.
  • E. UNY
    UNY is an Indonesian public university in Yogyakarta known for its strong focus on teacher education and educational sciences.
  • 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: SBU
Triple: [Southbury railway station, railcode, SBU]
Generated description
SBU is the three-letter station code used to identify Southbury railway station in the UK rail network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SBU
Target entity description: SBU is the three-letter station code used to identify Southbury railway station in the UK rail network.
  • A. SBU
    SBU is a major public research university in Tehran, Iran, known for its strong programs in engineering, humanities, and social sciences.
  • B. SBU
    SBU is the abbreviation for the Special Boarding Unit, an elite maritime special operations force of the Indian Navy.
  • C. SBU
    SBU is a major public research university located on Long Island, New York, known for its strong science, engineering, and medical programs.
  • D. SBU
    SBU is the main domestic security and intelligence agency of Ukraine, responsible for counterintelligence, counterterrorism, and protecting state secrets.
  • E. UNY
    UNY is an Indonesian public university in Yogyakarta known for its strong focus on teacher education and educational sciences.
  • 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_69d8d38974308190a9174430ef256b73 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e543cf33288190bc2cd6b7befde944 completed April 19, 2026, 9:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a04f88cb7c881909911b2c28a72fcf6 completed May 13, 2026, 10:17 p.m.
NEDg Description generation batch_6a04f9fc493881909ba9159748d4f3fb completed May 13, 2026, 10:23 p.m.
NED2 Entity disambiguation (via description) batch_6a04fad8daa88190961d643d30a52aa7 completed May 13, 2026, 10:27 p.m.
Created at: April 10, 2026, 11:43 a.m.