Triple

T15030209
Position Surface form Disambiguated ID Type / Status
Subject Green line (Stockholm metro) E378322 entity
Predicate hasTerminus P388 FINISHED
Object Hässelby gård
Hässelby gård is a residential district and Stockholm metro station in western Stockholm, Sweden, served by the Green line.
E1134020 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: Hässelby gård | Statement: [Green line (Stockholm metro), hasTerminus, Hässelby gård]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hässelby gård
Context triple: [Green line (Stockholm metro), hasTerminus, Hässelby gård]
  • A. Häggenås
    Häggenås is a small locality in Jämtland County, northern Sweden, situated within Östersund Municipality.
  • B. Rosengård
    Rosengård is a prominent Swedish football club based in Malmö, known for its successful women's team and history of developing world-class players.
  • C. Grubbegata
    Grubbegata is a street in central Oslo, Norway, known for running through the area that houses key government buildings and institutions.
  • D. Humlegården
    Humlegården is a large historic park in central Stockholm known for its green spaces, walking paths, and recreational areas.
  • E. Djursholm
    Djursholm is an affluent suburban district of Stockholm, Sweden, known for its villas, garden-city planning, and status as one of the country’s wealthiest residential areas.
  • 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: Hässelby gård
Triple: [Green line (Stockholm metro), hasTerminus, Hässelby gård]
Generated description
Hässelby gård is a residential district and Stockholm metro station in western Stockholm, Sweden, served by the Green line.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hässelby gård
Target entity description: Hässelby gård is a residential district and Stockholm metro station in western Stockholm, Sweden, served by the Green line.
  • A. Häggenås
    Häggenås is a small locality in Jämtland County, northern Sweden, situated within Östersund Municipality.
  • B. Rosengård
    Rosengård is a prominent Swedish football club based in Malmö, known for its successful women's team and history of developing world-class players.
  • C. Grubbegata
    Grubbegata is a street in central Oslo, Norway, known for running through the area that houses key government buildings and institutions.
  • D. Humlegården
    Humlegården is a large historic park in central Stockholm known for its green spaces, walking paths, and recreational areas.
  • E. Djursholm
    Djursholm is an affluent suburban district of Stockholm, Sweden, known for its villas, garden-city planning, and status as one of the country’s wealthiest residential areas.
  • 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_69d85cd46b2c819090d054c27787f677 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7e2416081908dfba48d7f7b4a84 completed April 15, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9dd967588190821cf47e9734db21 completed May 9, 2026, 2:37 a.m.
NEDg Description generation batch_69fe9e5dbbe0819084567688758b0245 completed May 9, 2026, 2:39 a.m.
NED2 Entity disambiguation (via description) batch_69fe9eedca1481908ce438991184d62e completed May 9, 2026, 2:41 a.m.
Created at: April 10, 2026, 2:59 a.m.