Triple

T16914369
Position Surface form Disambiguated ID Type / Status
Subject Helsinki tram network E410283 entity
Predicate hasDepot P2413 FINISHED
Object Koskelan varikko
Koskelan varikko is a major tram depot and maintenance facility serving the public transport system in Helsinki, Finland.
E1239879 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: Koskelan varikko | Statement: [Helsinki tram network, hasDepot, Koskelan varikko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Koskelan varikko
Context triple: [Helsinki tram network, hasDepot, Koskelan varikko]
  • A. Kyösti
    Kyösti is a Finnish masculine given name, notably borne by Kyösti Kallio, the fourth President of Finland.
  • B. Kylmäkoski
    Kylmäkoski is a former municipality in the Pirkanmaa region of Finland, now part of the town of Akaa.
  • C. Köyliö
    Köyliö is a small former municipality in western Finland known for its rural landscape and historical significance, particularly in the Satakunta region.
  • D. Siikainen
    Siikainen is a small rural municipality in western Finland known for its forests, lakes, and location within the Satakunta region.
  • E. Kotikaivolla
    Kotikaivolla is a literary work by Finnish writer Sylvi Kekkonen, reflecting her characteristic introspective and domestic themes.
  • 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: Koskelan varikko
Triple: [Helsinki tram network, hasDepot, Koskelan varikko]
Generated description
Koskelan varikko is a major tram depot and maintenance facility serving the public transport system in Helsinki, Finland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Koskelan varikko
Target entity description: Koskelan varikko is a major tram depot and maintenance facility serving the public transport system in Helsinki, Finland.
  • A. Kyösti
    Kyösti is a Finnish masculine given name, notably borne by Kyösti Kallio, the fourth President of Finland.
  • B. Kylmäkoski
    Kylmäkoski is a former municipality in the Pirkanmaa region of Finland, now part of the town of Akaa.
  • C. Köyliö
    Köyliö is a small former municipality in western Finland known for its rural landscape and historical significance, particularly in the Satakunta region.
  • D. Siikainen
    Siikainen is a small rural municipality in western Finland known for its forests, lakes, and location within the Satakunta region.
  • E. Kotikaivolla
    Kotikaivolla is a literary work by Finnish writer Sylvi Kekkonen, reflecting her characteristic introspective and domestic themes.
  • 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_69d886c7b1e481908c3766dfa8c13458 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3ca3f1a2c8190a512ccc09a080eb4 completed April 18, 2026, 6:15 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c7be679c8190b9d0b0b9cfe185d3 completed May 10, 2026, 6 p.m.
NEDg Description generation batch_6a00c9059a2c819099ede5a7b6e25b18 completed May 10, 2026, 6:05 p.m.
NED2 Entity disambiguation (via description) batch_6a00c9d1c6a0819083635b8246cc82e7 completed May 10, 2026, 6:09 p.m.
Created at: April 10, 2026, 5:30 a.m.