Triple

T21315372
Position Surface form Disambiguated ID Type / Status
Subject Parsons Green tube station E525455 entity
Predicate stationCode P1289 FINISHED
Object PGN
PGN is the three-letter station code for Parsons Green, a London Underground station on the District line in the London Borough of Hammersmith and Fulham.
 E1477135 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: PGN | Statement: [Parsons Green tube station, stationCode, PGN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: PGN
Context triple: [Parsons Green tube station, stationCode, PGN]
  • A. PGN
    PGN is the vehicle registration code assigned to the city of Gniezno in Poland.
  • B. PGN
    PGN is the commonly used acronym for Colombia’s Office of the Inspector General, the state body responsible for overseeing public officials and safeguarding public interests.
  • C. SGF
    SGF is the station code for South Gosforth Metro station on the Tyne and Wear Metro network in Newcastle upon Tyne, England.
  • D. PGPL
    PGPL is the top professional football league in Iran, featuring the country’s leading clubs in the highest tier of its league system.
  • E. PGL
    PGL is a prominent esports tournament organizer best known for hosting major Counter-Strike: Global Offensive championships and other competitive gaming events worldwide.
  • 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: PGN
Triple: [Parsons Green tube station, stationCode, PGN]
Generated description
PGN is the three-letter station code for Parsons Green, a London Underground station on the District line in the London Borough of Hammersmith and Fulham.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: PGN
Target entity description: PGN is the three-letter station code for Parsons Green, a London Underground station on the District line in the London Borough of Hammersmith and Fulham.
  • A. PGN
    PGN is the vehicle registration code assigned to the city of Gniezno in Poland.
  • B. PGN
    PGN is the commonly used acronym for Colombia’s Office of the Inspector General, the state body responsible for overseeing public officials and safeguarding public interests.
  • C. SGF
    SGF is the station code for South Gosforth Metro station on the Tyne and Wear Metro network in Newcastle upon Tyne, England.
  • D. PGPL
    PGPL is the top professional football league in Iran, featuring the country’s leading clubs in the highest tier of its league system.
  • E. PGL
    PGL is a prominent esports tournament organizer best known for hosting major Counter-Strike: Global Offensive championships and other competitive gaming events worldwide.
  • 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_69e0b51ad810819098c12392c8e55f6c completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e75dcf2534819097abbb2e9559e791 completed April 21, 2026, 11:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a099edb42a08190889785a096d3b7d7 completed May 17, 2026, 10:56 a.m.
NEDg Description generation batch_6a099f8c4a5c8190a67b3185fe8a02ad completed May 17, 2026, 10:59 a.m.
NED2 Entity disambiguation (via description) batch_6a099ffeb4b88190b2859b55ba356e22 completed May 17, 2026, 11:01 a.m.
Created at: April 16, 2026, 4:28 p.m.