Triple

T2790325
Position Surface form Disambiguated ID Type / Status
Subject Northern line E61912 entity
Predicate depot P14646 FINISHED
Object Morden depot
Morden depot is a major London Underground maintenance and stabling facility serving the Northern line at its southern end.
 E298520 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: Morden depot | Statement: [Northern line, depot, Morden depot]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Morden depot
Context triple: [Northern line, depot, Morden depot]
  • A. Langwasser depot
    Langwasser depot is a maintenance and storage facility serving the Nuremberg U-Bahn rapid transit system in Nuremberg, Germany.
  • B. Fürth depot
    Fürth depot is a maintenance and storage facility serving the Nuremberg U-Bahn rapid transit system in the Fürth area of Germany.
  • C. London Road depot
    London Road depot is a maintenance and stabling facility for London Underground trains serving the Bakerloo line near Waterloo in central London.
  • D. Carnide depot
    Carnide depot is a maintenance and storage facility serving the Lisbon Metro system in Lisbon, Portugal.
  • E. Gogar depot
    Gogar depot is the main maintenance and operations facility for the Edinburgh Trams light rail system in Edinburgh, Scotland.
  • 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: Morden depot
Triple: [Northern line, depot, Morden depot]
Generated description
Morden depot is a major London Underground maintenance and stabling facility serving the Northern line at its southern end.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Morden depot
Target entity description: Morden depot is a major London Underground maintenance and stabling facility serving the Northern line at its southern end.
  • A. Langwasser depot
    Langwasser depot is a maintenance and storage facility serving the Nuremberg U-Bahn rapid transit system in Nuremberg, Germany.
  • B. Fürth depot
    Fürth depot is a maintenance and storage facility serving the Nuremberg U-Bahn rapid transit system in the Fürth area of Germany.
  • C. London Road depot
    London Road depot is a maintenance and stabling facility for London Underground trains serving the Bakerloo line near Waterloo in central London.
  • D. Carnide depot
    Carnide depot is a maintenance and storage facility serving the Lisbon Metro system in Lisbon, Portugal.
  • E. Gogar depot
    Gogar depot is the main maintenance and operations facility for the Edinburgh Trams light rail system in Edinburgh, Scotland.
  • 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_69ab4b7f51d881908768300ebd2fbdae completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abddb4ef3081909122840a357801bf completed March 7, 2026, 8:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc65c1f848190b6efeefb64a3e131 completed March 10, 2026, 7:21 a.m.
NEDg Description generation batch_69afc6e6d4bc81908108fe24677448c3 completed March 10, 2026, 7:23 a.m.
NED2 Entity disambiguation (via description) batch_69afc7907be88190b70458ed735261e8 completed March 10, 2026, 7:26 a.m.
Created at: March 6, 2026, 9:58 p.m.