Triple

T2986091
Position Surface form Disambiguated ID Type / Status
Subject Hayes railway station (Bromley) E80627 entity
Predicate railcode P27071 FINISHED
Object HYS
HYS is the National Rail station code for Hayes railway station in the London Borough of Bromley.
 E315465 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: HYS | Statement: [Hayes railway station (Bromley), railcode, HYS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HYS
Context triple: [Hayes railway station (Bromley), railcode, HYS]
  • A. HY
    HY is the commonly used abbreviation for the University of Helsinki, a major research university in Finland.
  • B. TYS
    TYS is the IATA airport code for McGhee Tyson Airport, the primary commercial airport serving Knoxville, Tennessee, and the surrounding region.
  • C. HES
    HES is the commonly used abbreviation for Historic Environment Scotland, the public body responsible for protecting and promoting Scotland’s historic environment.
  • D. YSB
    YSB is the IATA airport code for Greater Sudbury Airport in Ontario, Canada.
  • E. HSS
    HSS (Home Subscriber Server) is a core network database in IP Multimedia Subsystem (IMS) architectures that manages user identities, subscription profiles, and authentication for telecom services.
  • 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: HYS
Triple: [Hayes railway station (Bromley), railcode, HYS]
Generated description
HYS is the National Rail station code for Hayes railway station in the London Borough of Bromley.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HYS
Target entity description: HYS is the National Rail station code for Hayes railway station in the London Borough of Bromley.
  • A. HY
    HY is the commonly used abbreviation for the University of Helsinki, a major research university in Finland.
  • B. TYS
    TYS is the IATA airport code for McGhee Tyson Airport, the primary commercial airport serving Knoxville, Tennessee, and the surrounding region.
  • C. HES
    HES is the commonly used abbreviation for Historic Environment Scotland, the public body responsible for protecting and promoting Scotland’s historic environment.
  • D. YSB
    YSB is the IATA airport code for Greater Sudbury Airport in Ontario, Canada.
  • E. HSS
    HSS (Home Subscriber Server) is a core network database in IP Multimedia Subsystem (IMS) architectures that manages user identities, subscription profiles, and authentication for telecom services.
  • 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_69ad8b16c3488190b47b6aa7a59a335b completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad99c76dfc8190b08bd6110ffabf25 completed March 8, 2026, 3:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b108fb46b08190bcbd00e69cf06047 completed March 11, 2026, 6:17 a.m.
NEDg Description generation batch_69b1098429f0819086767078b9687674 completed March 11, 2026, 6:19 a.m.
NED2 Entity disambiguation (via description) batch_69b109ea926481909c85a9aa28027d41 completed March 11, 2026, 6:21 a.m.
Created at: March 8, 2026, 2:59 p.m.