Triple

T20141867
Position Surface form Disambiguated ID Type / Status
Subject Garston railway station E491187 entity
Predicate hasStationCode P1289 FINISHED
Object GSN
GSN is the National Rail station code for Garston railway station in Liverpool, England.
 E1413643 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: GSN | Statement: [Garston railway station, hasStationCode, GSN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GSN
Context triple: [Garston railway station, hasStationCode, GSN]
  • A. GSN
    GSN is the FAA airport code for Saipan International Airport, the primary airport serving Saipan in the Northern Mariana Islands.
  • B. GSC
    GSC is the Geological Survey of Canada, the national scientific agency responsible for studying and mapping Canada’s geology, natural resources, and geological hazards.
  • C. GSC
    GSC is the commonly used abbreviation for the General Secretariat of the Council of the European Union, the administrative body that supports the Council’s work and decision-making processes.
  • D. GSC
    GSC is a collegiate athletic conference in the NCAA Division II primarily composed of universities in the southeastern United States.
  • E. GSC
    GSC is an astronomical instrument used on the MAXI X-ray observatory to detect and monitor cosmic X-ray sources.
  • 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: GSN
Triple: [Garston railway station, hasStationCode, GSN]
Generated description
GSN is the National Rail station code for Garston railway station in Liverpool, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GSN
Target entity description: GSN is the National Rail station code for Garston railway station in Liverpool, England.
  • A. GSN
    GSN is the FAA airport code for Saipan International Airport, the primary airport serving Saipan in the Northern Mariana Islands.
  • B. GSC
    GSC is the Geological Survey of Canada, the national scientific agency responsible for studying and mapping Canada’s geology, natural resources, and geological hazards.
  • C. GSC
    GSC is an astronomical instrument used on the MAXI X-ray observatory to detect and monitor cosmic X-ray sources.
  • D. GSC
    GSC is the commonly used abbreviation for the General Secretariat of the Council of the European Union, the administrative body that supports the Council’s work and decision-making processes.
  • E. GSC
    GSC is a collegiate athletic conference in the NCAA Division II primarily composed of universities 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e6679bcf2c8190ac6e969178d8acde completed April 20, 2026, 5:51 p.m.
NED1 Entity disambiguation (via context triple) batch_6a082de69fc08190bfef348685007aad completed May 16, 2026, 8:42 a.m.
NEDg Description generation batch_6a082fa951a88190b5c3cac2280d43b7 completed May 16, 2026, 8:49 a.m.
NED2 Entity disambiguation (via description) batch_6a08305a986481909e78c28b1c919c9f completed May 16, 2026, 8:52 a.m.
Created at: April 11, 2026, 11:33 p.m.