Triple

T22083624
Position Surface form Disambiguated ID Type / Status
Subject Staplehurst railway station E545713 entity
Predicate stationCode P1289 FINISHED
Object SPU
SPU is the National Rail station code for Staplehurst railway station in Kent, England.
 E1517259 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: SPU | Statement: [Staplehurst railway station, stationCode, SPU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SPU
Context triple: [Staplehurst railway station, stationCode, SPU]
  • A. SPU
    SPU is a private Christian liberal arts university located in Seattle, Washington.
  • B. SPU
    SPU is the three-letter IATA airport code for Split Airport, the main international airport serving the coastal city of Split in Croatia.
  • C. UWSP
    UWSP is a public university in Stevens Point, Wisconsin, known for its strong programs in natural resources, education, and the arts within the University of Wisconsin System.
  • D. SCU
    SCU is the IATA airport code for Antonio Maceo International Airport serving Santiago de Cuba, Cuba.
  • E. SCU
    SCU is the acronym for Egypt’s Supreme Council of Universities, the national body overseeing and coordinating higher education institutions in the country.
  • 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: SPU
Triple: [Staplehurst railway station, stationCode, SPU]
Generated description
SPU is the National Rail station code for Staplehurst railway station in Kent, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SPU
Target entity description: SPU is the National Rail station code for Staplehurst railway station in Kent, England.
  • A. SPU
    SPU is a private Christian liberal arts university located in Seattle, Washington.
  • B. SPU
    SPU is the three-letter IATA airport code for Split Airport, the main international airport serving the coastal city of Split in Croatia.
  • C. UWSP
    UWSP is a public university in Stevens Point, Wisconsin, known for its strong programs in natural resources, education, and the arts within the University of Wisconsin System.
  • D. SCU
    SCU is the IATA airport code for Antonio Maceo International Airport serving Santiago de Cuba, Cuba.
  • E. SCU
    SCU is the acronym for Egypt’s Supreme Council of Universities, the national body overseeing and coordinating higher education institutions in the country.
  • 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_69e11e3523488190badd54b5d580c00d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128b803f081909a0a121aecf526ae completed April 28, 2026, 9:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0a80bd85708190ba4217a96588a52a completed May 18, 2026, 3 a.m.
NEDg Description generation batch_6a0a8165238c81909f53f0c96ceda4dc completed May 18, 2026, 3:03 a.m.
NED2 Entity disambiguation (via description) batch_6a0a826075988190a7148ded16f779c0 completed May 18, 2026, 3:07 a.m.
Created at: April 16, 2026, 8:28 p.m.