Triple

T22553174
Position Surface form Disambiguated ID Type / Status
Subject St Bees railway station E557610 entity
Predicate hasStationCode P1289 FINISHED
Object SBS
SBS is the National Rail station code for St Bees railway station in Cumbria, England.
E1543329 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: SBS | Statement: [St Bees railway station, hasStationCode, SBS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SBS
Context triple: [St Bees railway station, hasStationCode, SBS]
  • A. SBS
    SBS is an elite British special forces unit of the Royal Navy specializing in maritime counter-terrorism, covert reconnaissance, and special operations.
  • B. SBS
    SBS is a South Korean public broadcasting organization known for its nationwide television and radio networks and popular entertainment, news, and drama programming.
  • C. SBS
    SBS is a post-nominal honorific used in Hong Kong to denote recipients of the Silver Bauhinia Star, a high-ranking government award for distinguished public service.
  • D. SBS
    SBS is the commonly used abbreviation for Santa Bárbara Sistemas, a Spanish defense contractor known for manufacturing military vehicles, weapons, and ammunition.
  • E. SBS
    SBS is the School of Biological Sciences at Nanyang Technological University, a major academic unit focused on education and research in the life 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: SBS
Triple: [St Bees railway station, hasStationCode, SBS]
Generated description
SBS is the National Rail station code for St Bees railway station in Cumbria, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: SBS
Target entity description: SBS is the National Rail station code for St Bees railway station in Cumbria, England.
  • A. SBS
    SBS is an elite British special forces unit of the Royal Navy specializing in maritime counter-terrorism, covert reconnaissance, and special operations.
  • B. SBS
    SBS is a South Korean public broadcasting organization known for its nationwide television and radio networks and popular entertainment, news, and drama programming.
  • C. SBS
    SBS is the commonly used abbreviation for Santa Bárbara Sistemas, a Spanish defense contractor known for manufacturing military vehicles, weapons, and ammunition.
  • D. SBS
    SBS is the School of Biological Sciences at Nanyang Technological University, a major academic unit focused on education and research in the life sciences.
  • E. SBS
    SBS is a post-nominal honorific used in Hong Kong to denote recipients of the Silver Bauhinia Star, a high-ranking government award for distinguished public service.
  • 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_69e11e59db848190b4272ecd2b690ffd completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15f775d308190b35a52310e9c84f7 completed April 29, 2026, 1:31 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b2d6510648190aba36f0ad1bb4f81 completed May 18, 2026, 3:16 p.m.
NEDg Description generation batch_6a0b364718308190937c3b7ae90ea9df completed May 18, 2026, 3:54 p.m.
NED2 Entity disambiguation (via description) batch_6a0b37a1ecc08190ac89e862582833a0 completed May 18, 2026, 4 p.m.
Created at: April 16, 2026, 8:52 p.m.