Triple

T13716414
Position Surface form Disambiguated ID Type / Status
Subject Sandown railway station E328910 entity
Predicate hasStationCode P1289 FINISHED
Object SAN
SAN is the National Rail station code for Sandown railway station on the Isle of Wight, England.
 E1058227 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: SAN | Statement: [Sandown railway station, hasStationCode, SAN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SAN
Context triple: [Sandown railway station, hasStationCode, SAN]
  • A. SAN
    SAN is the three-letter IATA airport code for San Diego International Airport, the primary commercial airport serving the San Diego, California area.
  • B. SAN
    SAN is the acronym for the Schuylkill Action Network, a collaborative partnership focused on protecting and restoring the Schuylkill River watershed.
  • C. SAN
    SAN is the stock ticker symbol for Banco Santander S.A., a major Spanish multinational banking and financial services company.
  • D. SAN
    SAN is the vehicle registration code used on license plates for vehicles registered in the Hof district of Bavaria, Germany.
  • E. SAM
    SAM is the official FIFA trigramme used to represent the Samoa national under-20 football team in international competitions and records.
  • 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: SAN
Triple: [Sandown railway station, hasStationCode, SAN]
Generated description
SAN is the National Rail station code for Sandown railway station on the Isle of Wight, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SAN
Target entity description: SAN is the National Rail station code for Sandown railway station on the Isle of Wight, England.
  • A. SAN
    SAN is the three-letter IATA airport code for San Diego International Airport, the primary commercial airport serving the San Diego, California area.
  • B. SAN
    SAN is the acronym for the Schuylkill Action Network, a collaborative partnership focused on protecting and restoring the Schuylkill River watershed.
  • C. SAN
    SAN is the stock ticker symbol for Banco Santander S.A., a major Spanish multinational banking and financial services company.
  • D. SAN
    SAN is the vehicle registration code used on license plates for vehicles registered in the Hof district of Bavaria, Germany.
  • E. SAM
    SAM is the commonly used abbreviation for Stade Athlétique Montluçonnais, a French rugby union club.
  • 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_69d80770b9bc81909f70c8c317d53cff completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dd4398f0448190810c840a82228706 completed April 13, 2026, 7:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69f79d5878948190a2aaab2ba31bd1ed completed May 3, 2026, 7:09 p.m.
NEDg Description generation batch_69f79e9e6ff88190b031fb1403cacabc completed May 3, 2026, 7:14 p.m.
NED2 Entity disambiguation (via description) batch_69f7a2d6e7ec81908a4cbc324e793c24 completed May 3, 2026, 7:32 p.m.
Created at: April 9, 2026, 9:54 p.m.