Triple

T4156234
Position Surface form Disambiguated ID Type / Status
Subject Swansea railway station E91421 entity
Predicate stationCode P1289 FINISHED
Object SWA
SWA is the National Rail station code for Swansea railway station, a major rail hub in Swansea, Wales.
 E417779 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: SWA | Statement: [Swansea railway station, stationCode, SWA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SWA
Context triple: [Swansea railway station, stationCode, SWA]
  • A. SWA
    SWA is the ICAO airline designator used to identify Southwest Airlines in aviation operations and air traffic control.
  • B. SWC
    SWC is the abbreviation for the Southwest Conference, a former NCAA Division I college athletic conference that primarily featured schools from Texas and the surrounding region.
  • C. SWC
    SWC is the acronym for the South Western Command of the Indian Army, a major operational command responsible for defense and military operations in India’s western sector.
  • D. SWP
    SWP is the commonly used acronym for California’s State Water Project, a massive water storage and delivery system supplying water to millions of residents and vast agricultural areas.
  • E. W&A
    W&A is the commonly used abbreviation for the Western and Atlantic Railroad, a historic rail line in the southeastern United States.
  • 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: SWA
Triple: [Swansea railway station, stationCode, SWA]
Generated description
SWA is the National Rail station code for Swansea railway station, a major rail hub in Swansea, Wales.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SWA
Target entity description: SWA is the National Rail station code for Swansea railway station, a major rail hub in Swansea, Wales.
  • A. SWA
    SWA is the ICAO airline designator used to identify Southwest Airlines in aviation operations and air traffic control.
  • B. SWC
    SWC is the abbreviation for the Southwest Conference, a former NCAA Division I college athletic conference that primarily featured schools from Texas and the surrounding region.
  • C. SWC
    SWC is the acronym for the South Western Command of the Indian Army, a major operational command responsible for defense and military operations in India’s western sector.
  • D. SWP
    SWP is the commonly used acronym for California’s State Water Project, a massive water storage and delivery system supplying water to millions of residents and vast agricultural areas.
  • E. W&A
    W&A is the commonly used abbreviation for the Western and Atlantic Railroad, a historic rail line in the southeastern United States.
  • 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_69aed9626ebc8190a39de631788bea3e completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af028fc11c819093fb2f616b97a694 completed March 9, 2026, 5:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69b57f3e3794819095659b7b51dfa742 completed March 14, 2026, 3:31 p.m.
NEDg Description generation batch_69b5803a2d00819084bcc4932846473e completed March 14, 2026, 3:35 p.m.
NED2 Entity disambiguation (via description) batch_69b580a0be508190b0410d2de905da71 completed March 14, 2026, 3:37 p.m.
Created at: March 9, 2026, 3:44 p.m.