Triple

T22348030
Position Surface form Disambiguated ID Type / Status
Subject Holland Park station E552447 entity
Predicate hasStationCode P1289 FINISHED
Object HPK
HPK is the National Rail station code used to identify Holland Park station in London’s public transport system.
 E1531038 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: HPK | Statement: [Holland Park station, hasStationCode, HPK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HPK
Context triple: [Holland Park station, hasStationCode, HPK]
  • A. HPK
    HPK is a professional ice hockey club from Hämeenlinna, Finland, competing in the country’s top-tier Liiga.
  • B. HPKCC
    HPKCC is a long-standing community organization in Chicago’s Hyde Park–Kenwood neighborhood that focuses on local advocacy, planning, and neighborhood improvement.
  • C. PKP
    PKP is Poland’s state-owned national railway operator, responsible for much of the country’s passenger and freight rail transport infrastructure.
  • D. KHPN
    KHPN is the ICAO airport code for Westchester County Airport, a regional airport serving Westchester County, New York and the surrounding area.
  • E. Hpakant
    Hpakant is a town in northern Myanmar renowned as the center of the country’s lucrative and often controversial jade mining industry.
  • 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: HPK
Triple: [Holland Park station, hasStationCode, HPK]
Generated description
HPK is the National Rail station code used to identify Holland Park station in London’s public transport system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HPK
Target entity description: HPK is the National Rail station code used to identify Holland Park station in London’s public transport system.
  • A. HPK
    HPK is a professional ice hockey club from Hämeenlinna, Finland, competing in the country’s top-tier Liiga.
  • B. HPKCC
    HPKCC is a long-standing community organization in Chicago’s Hyde Park–Kenwood neighborhood that focuses on local advocacy, planning, and neighborhood improvement.
  • C. PKP
    PKP is Poland’s state-owned national railway operator, responsible for much of the country’s passenger and freight rail transport infrastructure.
  • D. KHPN
    KHPN is the ICAO airport code for Westchester County Airport, a regional airport serving Westchester County, New York and the surrounding area.
  • E. Hpakant
    Hpakant is a town in northern Myanmar renowned as the center of the country’s lucrative and often controversial jade mining industry.
  • 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_69e11e4a0ad08190a385b4d343cf6524 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f157995bec819080b8d05fa88704ed completed April 29, 2026, 12:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ad5337cb48190b717d997d367551a completed May 18, 2026, 9 a.m.
NEDg Description generation batch_6a0ad9947a8481909b36b72d15432d63 completed May 18, 2026, 9:19 a.m.
NED2 Entity disambiguation (via description) batch_6a0ada8fe7208190bc1143e328abc112 completed May 18, 2026, 9:23 a.m.
Created at: April 16, 2026, 8:43 p.m.