Triple

T9168033
Position Surface form Disambiguated ID Type / Status
Subject Munkkiniemi E220012 entity
Predicate locatedNear P294 FINISHED
Object Haaga
Haaga is a residential district in western Helsinki, Finland, known for its parks, including the popular rhododendron garden, and good public transport connections.
E782392 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: Haaga | Statement: [Munkkiniemi, locatedNear, Haaga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haaga
Context triple: [Munkkiniemi, locatedNear, Haaga]
  • A. Harjola
    Harjola is a Finnish surname, notably borne by film director Renny Harlin (born Lauri Mauritz Harjola).
  • B. Hassela
    Hassela is a small rural locality in northern Sweden known for its forested landscape and nearby ski and outdoor recreation areas.
  • C. Hassel
    Hassel is a Norwegian surname most notably borne by Nobel Prize–winning chemist Odd Hassel.
  • D.
    Hå is a coastal municipality in southwestern Norway known for its agricultural landscape, beaches, and location along the North Sea in Rogaland county.
  • E. Harauti
    Harauti is an Indo-Aryan dialect of the Rajasthani language spoken primarily in the Hadoti region of Rajasthan, India.
  • 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: Haaga
Triple: [Munkkiniemi, locatedNear, Haaga]
Generated description
Haaga is a residential district in western Helsinki, Finland, known for its parks, including the popular rhododendron garden, and good public transport connections.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Haaga
Target entity description: Haaga is a residential district in western Helsinki, Finland, known for its parks, including the popular rhododendron garden, and good public transport connections.
  • A. Harjola
    Harjola is a Finnish surname, notably borne by film director Renny Harlin (born Lauri Mauritz Harjola).
  • B. Hassela
    Hassela is a small rural locality in northern Sweden known for its forested landscape and nearby ski and outdoor recreation areas.
  • C. Hassel
    Hassel is a Norwegian surname most notably borne by Nobel Prize–winning chemist Odd Hassel.
  • D.
    Hå is a coastal municipality in southwestern Norway known for its agricultural landscape, beaches, and location along the North Sea in Rogaland county.
  • E. Harauti
    Harauti is an Indo-Aryan dialect of the Rajasthani language spoken primarily in the Hadoti region of Rajasthan, India.
  • 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_69ca83e467108190abcae6a33b3d4dad completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccaadfb50881909b9127f92e4b3e21 completed April 1, 2026, 5:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69d05491ccec819093fcf2d764c5381b completed April 4, 2026, midnight
NEDg Description generation batch_69d05628d8708190a85437c5051a5a05 completed April 4, 2026, 12:07 a.m.
NED2 Entity disambiguation (via description) batch_69d056e4ad98819086e73edf15aa6210 completed April 4, 2026, 12:10 a.m.
Created at: March 30, 2026, 7:22 p.m.