{
  "description": "系统发育信息提取 - In-Context Learning示例 (基于PlantScience.ai论文描述)",
  "examples": [
    {
      "example_id": 1,
      "text": "The phylogenetic analysis revealed that the Arabidopsis thaliana SPL family consists of 16 members, which can be divided into seven groups (Group I to Group VII) based on their phylogenetic relationships and structural characteristics.",
      "extraction": {
        "gene_family": "SPL",
        "species": "Arabidopsis thaliana",
        "total_genes": 16,
        "groups": {
          "Group_I": [],
          "Group_II": [],
          "Group_III": [],
          "Group_IV": [],
          "Group_V": [],
          "Group_VI": [],
          "Group_VII": []
        }
      },
      "reasoning": "从文本中提取基因家族名称(SPL)、物种(Arabidopsis thaliana)、总基因数(16)和分组数(7个组，Group I-VII)"
    },
    {
      "example_id": 2,
      "text": "In tomato (Solanum lycopersicum), a total of 233 P450 genes were identified and classified into 48 groups. The largest group is Group 71 containing 43 genes, followed by Group 72 with 20 genes.",
      "extraction": {
        "gene_family": "P450",
        "species": "Solanum lycopersicum",
        "total_genes": 233,
        "groups": {
          "Group_71": ["CYP71D184", "CYP71D185", "..."],
          "Group_72": ["CYP72A1", "CYP72A2", "..."]
        }
      },
      "reasoning": "提取基因家族(P450)、物种(番茄)、总基因数(233)、分组数(48)，并识别最大的两个分组(Group_71: 43个基因, Group_72: 20个基因)"
    },
    {
      "example_id": 3,
      "text": "The AP2/ERF gene family in Tartary buckwheat (Fagopyrum tataricum) comprises 146 members distributed across 12 groups. Group I contains 35 genes including FtAP2-1 to FtAP2-35, while Group II has 28 genes.",
      "extraction": {
        "gene_family": "AP2/ERF",
        "species": "Fagopyrum tataricum",
        "total_genes": 146,
        "groups": {
          "Group_I": ["FtAP2-1", "FtAP2-2", "...", "FtAP2-35"],
          "Group_II": ["FtERF-1", "FtERF-2", "..."]
        }
      },
      "reasoning": "提取基因家族(AP2/ERF)、物种(苦荞)、总基因数(146)、分组数(12)，并详细列出Group I的35个基因命名格式"
    },
    {
      "example_id": 4,
      "text": "Phylogenetic analysis of the WRKY family in rice (Oryza sativa) identified 102 genes classified into three major groups: Group I (38 genes), Group II (45 genes), and Group III (19 genes).",
      "extraction": {
        "gene_family": "WRKY",
        "species": "Oryza sativa",
        "total_genes": 102,
        "groups": {
          "Group_I": ["OsWRKY1", "OsWRKY2", "..."],
          "Group_II": ["OsWRKY39", "OsWRKY40", "..."],
          "Group_III": ["OsWRKY84", "OsWRKY85", "..."]
        }
      },
      "reasoning": "提取基因家族(WRKY)、物种(水稻)、总基因数(102)，以及3个分组及其基因数(Group I: 38, Group II: 45, Group III: 19)"
    },
    {
      "example_id": 5,
      "text": "A comprehensive analysis of the MYB transcription factor family in potato (Solanum tuberosum) revealed 198 members. These genes were divided into 25 subgroups based on phylogenetic relationships, with subgroup 1 being the largest containing 22 genes.",
      "extraction": {
        "gene_family": "MYB",
        "species": "Solanum tuberosum",
        "total_genes": 198,
        "groups": {
          "Subgroup_1": ["StMYB1", "StMYB2", "..."],
          "Subgroup_2": [],
          "Subgroup_3": []
        }
      },
      "reasoning": "提取基因家族(MYB)、物种(马铃薯)、总基因数(198)、分组数(25个subgroups)，并识别最大分组(subgroup 1: 22个基因)"
    }
  ],
  "extraction_rules": [
    "基因家族名称通常在标题或摘要中明确提及",
    "物种名使用拉丁学名(如Solanum lycopersicum)",
    "总基因数是明确的数字，通常与'identified'、'comprises'、'consists of'等词一起出现",
    "分组信息可能用'group'、'subgroup'、'clade'、'cluster'等词描述",
    "基因ID格式因物种而异，如AtSPL1(拟南芥)、SlCYP71D1(番茄)、FtAP2-1(苦荞)",
    "如果文本中没有具体的基因列表，只记录分组名称"
  ],
  "scrutiny_questions": [
    "是否提取了所有提到的基因家族？",
    "是否遗漏了任何分组信息？",
    "提取的基因数是否与文本描述一致？",
    "是否有分组包含的基因数超过总基因数？",
    "是否混淆了不同基因家族的信息？"
  ]
}