Triple

T2844788
Position Surface form Disambiguated ID Type / Status
Subject Piccadilly line E62557 entity
Predicate depot P14646 FINISHED
Object Cockfosters depot
Cockfosters depot is a major London Underground maintenance and stabling facility serving the Piccadilly line at its northeastern terminus in Cockfosters.
E304079 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: Cockfosters depot | Statement: [Piccadilly line, depot, Cockfosters depot]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cockfosters depot
Context triple: [Piccadilly line, depot, Cockfosters depot]
  • A. Queens Road depot
    Queens Road depot is a major tram maintenance and operations facility serving the Manchester Metrolink light rail network.
  • B. Barking depot
    Barking depot is a London Underground maintenance and stabling facility serving trains on the Hammersmith & City line.
  • 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. Hammersmith depot
    Hammersmith depot is a London Underground maintenance and stabling facility primarily serving the Circle and Hammersmith & City lines.
  • E. Neasden Depot
    Neasden Depot is a major London Underground maintenance and stabling facility serving trains on the Metropolitan line.
  • 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: Cockfosters depot
Triple: [Piccadilly line, depot, Cockfosters depot]
Generated description
Cockfosters depot is a major London Underground maintenance and stabling facility serving the Piccadilly line at its northeastern terminus in Cockfosters.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Cockfosters depot
Target entity description: Cockfosters depot is a major London Underground maintenance and stabling facility serving the Piccadilly line at its northeastern terminus in Cockfosters.
  • A. Queens Road depot
    Queens Road depot is a major tram maintenance and operations facility serving the Manchester Metrolink light rail network.
  • B. Barking depot
    Barking depot is a London Underground maintenance and stabling facility serving trains on the Hammersmith & City line.
  • 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. Hammersmith depot
    Hammersmith depot is a London Underground maintenance and stabling facility primarily serving the Circle and Hammersmith & City lines.
  • E. Neasden Depot
    Neasden Depot is a major London Underground maintenance and stabling facility serving trains on the Metropolitan line.
  • 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_69ab4c3d16bc81908b3a1c98fbd287fe completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abdf1b58c88190b45d8c5a76dc52ac completed March 7, 2026, 8:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69afe8d850b481909850ff5e89021824 completed March 10, 2026, 9:48 a.m.
NEDg Description generation batch_69afe990ce088190b42b20037c1eef3f completed March 10, 2026, 9:51 a.m.
NED2 Entity disambiguation (via description) batch_69b00d04f42081909d59e1ad1bec6c34 completed March 10, 2026, 12:22 p.m.
Created at: March 6, 2026, 10:02 p.m.