Question–answering (QA) systems have proven to be helpful, especially to those who feel uncomfortable entering keywords, sometimes extended with search symbols such as +, *, and so forth. In developing such systems, the main focus has been on the enhanced retrieval performance of searches, and recent trends in QA systems center on the extraction of exact answers. However, when their usability was evaluated, some users indicated that they found it difficult to accept the answers because of the absence of supporting context and rationale. Current approaches to address this problem include providing answers with linking paragraphs or with summarizing extensions. Both methods are believed to be sufficient to answer questions seeking the names of objects or quantities that have only a single answer. However, neither method addresses the situation when an answer requires the comparison and integration of information appearing in multiple documents or in several places in a single document. This paper argues that coherent answer generation is crucial for such questions, and that the key to this coherence is to analyze texts to a level beyond sentence annotations. To demonstrate this idea, a prototype has been developed based on rhetorical structure theory, and a preliminary evaluation has been carried out. The evaluation indicates that users prefer to see the extended answers that can be generated using such semantic annotations, provided that additional context and rationale information are made available.