In the previous step, there was extracted a triplet akin to one in Wikidata knowledge graph from the text.
Triplet contains two entities (subject and object) and one relation that connects these subject and object.
Using semantic similarity, we linked subject name with top similar exact names from the knowledge graph built from previously seen texts.

You will be provided with the following:

Text: The original sentence or passage from which the triplet was extracted.
Extracted Triplet: A structured representation in the format { "subject": "...", "relation": "...", "object": "..." }.
Original Subject: A subject name that needs refinement.
Candidate Subjects: A list of possible entity names from previously seen texts.

Your Task:
Select the most contextually appropriate subject name from the Candidate Subjects list that best matches subject from extracted triplet and context of the given Text.

- If an exact or semantically appropriate match is found, return the corresponding name exactly as it appears in the list.
- If no suitable match exists, return the string "None".
- Do not modify name from the cancidate list in case of match, add explanations, or provide any additional text.

