Triple

T6884448
Position Surface form Disambiguated ID Type / Status
Subject Tweedbank railway station E158880 entity
Predicate hasStationCode P1289 FINISHED
Object TWB
TWB is the National Rail station code for Tweedbank railway station in the Scottish Borders, Scotland.
 E625952 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: TWB | Statement: [Tweedbank railway station, hasStationCode, TWB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: TWB
Context triple: [Tweedbank railway station, hasStationCode, TWB]
  • A. TWB
    TWB is the IATA airport code for Toowoomba City Aerodrome, a regional airport serving the city of Toowoomba in Queensland, Australia.
  • B. TWB
    TWB is the ICAO airline designator assigned to the South Korean low-cost carrier Tʼway Air.
  • C. TWG
    TWG is the commonly used abbreviation for The World Games, an international multi-sport event featuring disciplines not contested in the Olympic Games.
  • D. YTWB
    YTWB is the ICAO airport code for Toowoomba City Aerodrome, a regional airport serving the city of Toowoomba in Queensland, Australia.
  • E. WB
    WB is the official vehicle registration code used for motor vehicles registered in the Indian state of West Bengal.
  • 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: TWB
Triple: [Tweedbank railway station, hasStationCode, TWB]
Generated description
TWB is the National Rail station code for Tweedbank railway station in the Scottish Borders, Scotland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: TWB
Target entity description: TWB is the National Rail station code for Tweedbank railway station in the Scottish Borders, Scotland.
  • A. TWB
    TWB is the IATA airport code for Toowoomba City Aerodrome, a regional airport serving the city of Toowoomba in Queensland, Australia.
  • B. TWB
    TWB is the ICAO airline designator assigned to the South Korean low-cost carrier Tʼway Air.
  • C. TWG
    TWG is the commonly used abbreviation for The World Games, an international multi-sport event featuring disciplines not contested in the Olympic Games.
  • D. YTWB
    YTWB is the ICAO airport code for Toowoomba City Aerodrome, a regional airport serving the city of Toowoomba in Queensland, Australia.
  • E. WB
    WB is the official vehicle registration code used for motor vehicles registered in the Indian state of West Bengal.
  • 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_69c688342f6c8190ad7eea6ba262db99 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d90a2590819092ff253dd66ebe8b completed March 27, 2026, 7:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69c742d652088190a65e06eb7fe79cfc completed March 28, 2026, 2:54 a.m.
NEDg Description generation batch_69c7441117ec8190b9b355c474289010 completed March 28, 2026, 2:59 a.m.
NED2 Entity disambiguation (via description) batch_69c744a20bd481908a7c6aaa6383a68f completed March 28, 2026, 3:01 a.m.
Created at: March 27, 2026, 2:23 p.m.