Triple

T11552737
Position Surface form Disambiguated ID Type / Status
Subject Shenstone railway station E273935 entity
Predicate hasStationCode P1289 FINISHED
Object SEN
SEN is the National Rail station code for Shenstone railway station in Staffordshire, England.
 E932747 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: SEN | Statement: [Shenstone railway station, hasStationCode, SEN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SEN
Context triple: [Shenstone railway station, hasStationCode, SEN]
  • A. SEN
    SEN is the three-letter IATA airport code for London Southend Airport in the United Kingdom.
  • B. SEL
    SEL is the former IATA airport code that once designated Seoul’s main international airport before it was replaced by newer facilities.
  • C. ENS
    ENS is a common abbreviation for the École Normale Supérieure, a prestigious French grande école known for its elite training in the sciences and humanities.
  • D. SED
    SED was the ruling Marxist–Leninist party that governed East Germany (the German Democratic Republic) from its founding in 1949 until the end of communist rule in 1989.
  • E. SER
    SER is the commonly used abbreviation for South Eastern Railway, a major railway zone in India.
  • 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: SEN
Triple: [Shenstone railway station, hasStationCode, SEN]
Generated description
SEN is the National Rail station code for Shenstone railway station in Staffordshire, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SEN
Target entity description: SEN is the National Rail station code for Shenstone railway station in Staffordshire, England.
  • A. SEN
    SEN is the three-letter IATA airport code for London Southend Airport in the United Kingdom.
  • B. SEL
    SEL is the former IATA airport code that once designated Seoul’s main international airport before it was replaced by newer facilities.
  • C. ENS
    ENS is a common abbreviation for the École Normale Supérieure, a prestigious French grande école known for its elite training in the sciences and humanities.
  • D. SED
    SED was the ruling Marxist–Leninist party that governed East Germany (the German Democratic Republic) from its founding in 1949 until the end of communist rule in 1989.
  • E. SER
    SER is the commonly used abbreviation for South Eastern Railway, a major railway zone in India.
  • 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_69d6aae4dfa48190a3ab0b19a159a3c5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d88a85b9ac8190a57c1fdaeacbe3d6 completed April 10, 2026, 5:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69e6e851a6688190996580a077496833 completed April 21, 2026, 3 a.m.
NEDg Description generation batch_69e6ef93e7d88190af3853b82de23c1b completed April 21, 2026, 3:31 a.m.
NED2 Entity disambiguation (via description) batch_69e6f9144afc819081ee7f78e32ad39a completed April 21, 2026, 4:12 a.m.
Created at: April 8, 2026, 9:37 p.m.