Triple

T46302
Position Surface form Disambiguated ID Type / Status
Subject Manchester Piccadilly E907 entity
Predicate stationCode P1289 FINISHED
Object MAN
MAN is the three-letter National Rail station code for Manchester Piccadilly, the main railway station in Manchester, England.
 E3870 NE FINISHED

How this triple was built (5 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: MAN | Statement: [Manchester Piccadilly, stationCode, MAN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MAN
Context triple: [Manchester Piccadilly, stationCode, MAN]
  • A. MAN
    MAN is the three-letter IATA airport code for Manchester Airport, a major international airport serving the Greater Manchester area in England.
  • B. Mark
    Mark is the given name of Mark Zuckerberg, the American technology entrepreneur and co-founder of Facebook.
  • C. NAM
    NAM is the commonly used acronym for the National Academy of Medicine, a leading U.S. nonprofit institution that provides expert advice on health, medicine, and biomedical science.
  • D. Lee
    Lee is a given name shared by numerous individuals across different cultures and professions.
  • E. El
    El is the common nickname for Philadelphia’s elevated Market–Frankford rapid transit line operated by SEPTA.
  • 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: MAN
Triple: [Manchester Piccadilly, stationCode, MAN]
Generated description
MAN is the three-letter National Rail station code for Manchester Piccadilly, the main railway station in Manchester, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MAN
Target entity description: MAN is the three-letter National Rail station code for Manchester Piccadilly, the main railway station in Manchester, England.
  • A. MAN chosen
    MAN is the three-letter IATA airport code for Manchester Airport, a major international airport serving the Greater Manchester area in England.
  • B. Mark
    Mark is the given name of Mark Zuckerberg, the American technology entrepreneur and co-founder of Facebook.
  • C. NAM
    NAM is the commonly used acronym for the National Academy of Medicine, a leading U.S. nonprofit institution that provides expert advice on health, medicine, and biomedical science.
  • D. Lee
    Lee is a given name shared by numerous individuals across different cultures and professions.
  • E. El
    El is the common nickname for Philadelphia’s elevated Market–Frankford rapid transit line operated by SEPTA.
  • F. None of above.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: stationCode
Context triple: [Manchester Piccadilly, stationCode, MAN]
  • A. hasStationCode chosen
    Indicates that an entity is associated with a specific station identification code.
  • B. hasRailStation
    Indicates that one entity possesses, contains, or is served by a rail station.
  • C. hasRailwayStation
    Indicates that a place or location is served by, or contains, a railway station.
  • D. numberOfStations
    Indicates the total count of stations associated with or contained by a given entity.
  • E. primaryStation
    Indicates that one station is designated as the main or principal station associated with another entity or within a given context.
  • F. None of above.

Provenance (6 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_69a2480baefc81909951b14058479aa2 completed Feb. 28, 2026, 1:42 a.m.
NER Named-entity recognition batch_69a24b1bf2c081908f20e13939b713ff completed Feb. 28, 2026, 1:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69a255355c988190b0916d74ff11340d completed Feb. 28, 2026, 2:38 a.m.
NEDg Description generation batch_69a255cce9fc81908ce7af16eed38024 completed Feb. 28, 2026, 2:41 a.m.
NED2 Entity disambiguation (via description) batch_69a256a5649c8190a964820ca25cd00b completed Feb. 28, 2026, 2:44 a.m.
PD Predicate disambiguation batch_69a24abd07508190a83ffba5368c1c79 completed Feb. 28, 2026, 1:54 a.m.
Created at: Feb. 28, 2026, 1:47 a.m.