Triple

T9716140
Position Surface form Disambiguated ID Type / Status
Subject Hungerford railway station E235146 entity
Predicate stationCode P1289 FINISHED
Object HGD
HGD is the National Rail station code for Hungerford railway station in Berkshire, England.
 E815968 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: HGD | Statement: [Hungerford railway station, stationCode, HGD]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HGD
Context triple: [Hungerford railway station, stationCode, HGD]
  • A. HGS
    HGS is the National Rail station code assigned to Hastings railway station in East Sussex, England.
  • B. ГД
    ГД is the station code used to designate the Gostiyny Dvor metro station in Saint Petersburg, Russia.
  • C. HGA
    HGA is a multidisciplinary architecture and engineering firm known for designing innovative, human-centered buildings and environments across sectors such as healthcare, education, and the arts.
  • D. HGF
    HGF is the abbreviation for the Helmholtz Association, Germany’s largest scientific research organization spanning multiple disciplines and large-scale facilities.
  • E. HGF
    HGF is the National Rail station code for Hag Fold railway station in Greater Manchester, England.
  • 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: HGD
Triple: [Hungerford railway station, stationCode, HGD]
Generated description
HGD is the National Rail station code for Hungerford railway station in Berkshire, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HGD
Target entity description: HGD is the National Rail station code for Hungerford railway station in Berkshire, England.
  • A. HGS
    HGS is the National Rail station code assigned to Hastings railway station in East Sussex, England.
  • B. ГД
    ГД is the station code used to designate the Gostiyny Dvor metro station in Saint Petersburg, Russia.
  • C. HGA
    HGA is a multidisciplinary architecture and engineering firm known for designing innovative, human-centered buildings and environments across sectors such as healthcare, education, and the arts.
  • D. HGF
    HGF is the National Rail station code for Hag Fold railway station in Greater Manchester, England.
  • E. HGF
    HGF is the abbreviation for the Helmholtz Association, Germany’s largest scientific research organization spanning multiple disciplines and large-scale facilities.
  • 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_69ca84cd8fa0819090a5e243ceb37003 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9e0bb82081908e21a646f4de1a61 completed April 1, 2026, 10:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19f941b908190a3e27f4b6c1b3535 completed April 4, 2026, 11:32 p.m.
NEDg Description generation batch_69d1a00eafc08190a2be7684fd7e9320 completed April 4, 2026, 11:34 p.m.
NED2 Entity disambiguation (via description) batch_69d1a072e08c8190a3beaf1219fa850f completed April 4, 2026, 11:36 p.m.
Created at: March 30, 2026, 8:20 p.m.