frontend/src/data/prompts.json

[
  {
    "item_id": "help-with-thumbs_up__sync",
    "canonical_item_id": "speech_action_silent_rel_sync",
    "modality_combination": "Speech + Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      }
    },
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs, then at one synchronized moment the person clearly says the single word “help” while at the same time the right hand forms and holds a clear thumbs-up pose with the thumb extended upward. The speech is audible and easy to distinguish, and the right-hand thumbs-up is clearly recognizable as a pose rather than a hand-raising motion. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-with-thumbs_up__sync_count",
    "canonical_item_id": "speech_action_silent_rel_sync_count",
    "modality_combination": "Speech + Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      }
    },
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action"
        ],
        "count": 2
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs visible, and both hands initially resting on the knees or thighs. The person performs the synchronized bundle twice: each time, the person clearly says the single word “help” while the right hand forms and holds a clearly recognizable thumbs-up pose with the thumb extended upward. The two synchronized repetitions are distinct, with a brief reset between them if needed, and no other words are spoken. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-then-thumbs_up__order",
    "canonical_item_id": "speech_action_silent_rel_order_speech_then_silent_action",
    "modality_combination": "Speech + Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "speech",
          "silent_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, Person A clearly says the single word “help” in an audible, easy-to-distinguish voice. After that speech ends, Person A forms and holds a clear thumbs-up pose with the right hand, with the fist closed and the thumb extended upward. After the final event, no new target action occurs."
  },
  {
    "item_id": "thumbs_up-then-help__order",
    "canonical_item_id": "speech_action_silent_rel_order_silent_action_then_speech",
    "modality_combination": "Speech + Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "silent_action",
          "speech"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with a full view of the face, mouth, upper body, both hands, and thighs; they begin seated on a chair with both hands resting on the knees or thighs. First, Person A forms and holds a clear thumbs-up pose with the right hand, with the fist closed and the thumb extended upward, while staying seated. After that gesture is clearly visible, Person A clearly says the single word “help” in an audible, easy-to-distinguish voice. The thumbs-up comes before the speech, and the speech contains no extra words. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-with-slap__sync",
    "canonical_item_id": "speech_action_sounding_rel_sync",
    "modality_combination": "Speech + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot with full face, mouth, upper body, both hands, and thighs visible, and both hands initially resting on the knees or thighs. The person clearly says the single word “help” while at the same moment the person’s left hand strikes the top of the left thigh, producing a sharp slap sound exactly at impact. The speech and the thigh slap occur synchronized as one event, with the mouth clearly visible during the word and the contact point clearly visible at the left thigh. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-with-slap__sync_count",
    "canonical_item_id": "speech_action_sounding_rel_sync_count",
    "modality_combination": "Speech + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "sounding_action"
        ],
        "count": 2
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera on a chair with both hands initially resting on the knees or thighs, and the full face, mouth, upper body, both hands, and thighs stay clearly visible. The person clearly says the single word “help” while the left hand strikes the top of the left thigh at the same moment, making visible contact and a sharp slap sound exactly at impact. This synchronized speech-plus-slap action happens exactly twice, with a brief reset between the two repetitions so the second pair can be seen and heard clearly. No extra words are spoken and no extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-then-slap__order",
    "canonical_item_id": "speech_action_sounding_rel_order_speech_then_sounding_action",
    "modality_combination": "Speech + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "speech",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "A single seated person faces the camera in a plain indoor room, shown in a static medium shot with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. Person A clearly says the single word “help,” with the mouth visible and no extra words. After that speech finishes, Person A lifts the left hand and slaps the top of the left thigh, making visible contact and producing one sharp slap sound at the moment of impact. After the final event, no new target action occurs."
  },
  {
    "item_id": "slap-then-help__order",
    "canonical_item_id": "speech_action_sounding_rel_order_sounding_action_then_speech",
    "modality_combination": "Speech + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "sounding_action",
          "speech"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person lifts the left hand and slaps the top of the left thigh, making clear visible contact and a sharp slap sound. After that action is completed, the person clearly says the single word “help” once, audibly and without any extra words. After the final event, no new target action occurs."
  },
  {
    "item_id": "thumbs_up-with-slap__sync",
    "canonical_item_id": "action_silent_action_sounding_rel_sync",
    "modality_combination": "Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs visible. The person begins seated on a chair with both hands resting on the knees or thighs. At one synchronized moment, the right hand holds a clear thumbs-up pose with the thumb extended upward while the left hand strikes the top of the left thigh, making visible contact and producing a sharp slap sound at the instant of impact. The thumbs-up is held clearly during the slap so both required events are visible together. After the final event, no new target action occurs."
  },
  {
    "item_id": "thumbs_up-with-slap__sync_count",
    "canonical_item_id": "action_silent_action_sounding_rel_sync_count",
    "modality_combination": "Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "silent_action",
          "sounding_action"
        ],
        "count": 2
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot with full face, mouth, upper body, both hands, and thighs visible, and both hands start resting on the knees or thighs. The person makes a clear right-hand thumbs-up pose, with the right hand held as a closed fist and the thumb extended upward, while the left hand strikes the top of the left thigh so the contact is visible and a sharp slap sound occurs at the same moment. This synchronized thumbs-up and thigh-slap bundle happens exactly twice, with a brief reset between the two repetitions while keeping the pose and contact easy to see and hear. After the final event, no new target action occurs."
  },
  {
    "item_id": "thumbs_up-then-slap__order",
    "canonical_item_id": "action_silent_action_sounding_rel_order_silent_action_then_sounding_action",
    "modality_combination": "Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible; they start with both hands resting on their thighs. First, the person forms and holds a clear right-handed thumbs-up pose, with the right fist closed and the thumb extended upward, and this pose is clearly visible before anything else happens. After that completed pose, the person brings the left hand down to strike the top of the left thigh once, making visible contact and producing a sharp slap sound at the moment of impact. The thumbs-up is not repeated during the slap, and the slap happens only after the thumbs-up is already established. After the final event, no new target action occurs."
  },
  {
    "item_id": "slap-then-thumbs_up__order",
    "canonical_item_id": "action_silent_action_sounding_rel_order_sounding_action_then_silent_action",
    "modality_combination": "Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "sounding_action",
          "silent_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the left hand strikes the top of the left thigh once, making clear visible contact and a sharp slap sound at the moment of impact. After that action is completed, the right hand forms and holds a clear thumbs-up pose with the thumb extended upward. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-with-thumbs_up-with-slap__sync",
    "canonical_item_id": "speech_action_silent_action_sounding_rel_sync",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs, then performs all three target events at the same time: clearly says the word “help,” holds the right hand in a visible thumbs-up pose, and strikes the top of the left thigh with the left hand so the slap is seen and a sharp slap sound occurs exactly at impact. The speech is only the single word “help,” with no extra words. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-with-thumbs_up-with-slap__sync_count",
    "canonical_item_id": "speech_action_silent_action_sounding_rel_sync_count",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ],
        "count": 2
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room with a static medium shot, one seated person facing the camera is visible with the full face, mouth, upper body, both hands, and thighs clearly in view, and both hands start resting on the knees or thighs. The person performs a synchronized bundle twice: saying the single word “help” clearly and audibly while holding the right hand in a recognizable thumbs-up pose, and at the same moment the left hand strikes the top of the left thigh to produce a sharp slap sound. Between the two repetitions, there is only a brief natural reset, and the same three events happen together again with the same timing and visibility. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-then-thumbs_up-then-slap__order",
    "canonical_item_id": "speech_action_silent_action_sounding_rel_order_speech_then_silent_action_then_sounding_action",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "speech",
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera on a chair with both hands initially resting on the knees or thighs, and the full face, mouth, upper body, both hands, and thighs stay clearly visible. First, the person clearly says the single word “help” with no extra words. After that speech is completed, the person forms and holds a clear thumbs-up with the right hand, with the thumb extended upward. After that pose is visible, the left hand strikes the top of the left thigh once, making visible contact and a sharp slap sound at the moment of impact. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-then-slap-then-thumbs_up__order",
    "canonical_item_id": "speech_action_silent_action_sounding_rel_order_speech_then_sounding_action_then_silent_action",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "speech",
          "sounding_action",
          "silent_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the thighs or knees. First, the person clearly says “help” once and only once. After that finishes, the person’s left hand strikes the top of the left thigh exactly once, with a visible impact and a sharp slap sound at the moment of contact. After that, the person forms and holds a clear thumbs-up pose with the right hand, showing a closed fist with the thumb extended upward. After the final event, no new target action occurs."
  },
  {
    "item_id": "thumbs_up-then-help-then-slap__order",
    "canonical_item_id": "speech_action_silent_action_sounding_rel_order_silent_action_then_speech_then_sounding_action",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "silent_action",
          "speech",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs visible; the person starts seated on a chair with both hands resting on the knees or thighs. First, the person forms and holds a clear thumbs-up with the right hand, with the fist closed and thumb extended upward. After that pose is complete, the person clearly says “help” and nothing else. After the speech ends, the person strikes the top of the left thigh with the left hand, making visible contact and producing one sharp slap sound at the moment of impact. After the final event, no new target action occurs."
  },
  {
    "item_id": "thumbs_up-then-slap-then-help__order",
    "canonical_item_id": "speech_action_silent_action_sounding_rel_order_silent_action_then_sounding_action_then_speech",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "silent_action",
          "sounding_action",
          "speech"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera on a chair, with the full face, mouth, upper body, both hands, and thighs visible, and both hands initially resting on the knees or thighs. The person first holds a clear thumbs-up pose with the right hand, with the fist closed and the thumb extended upward. After that pose is completed, the person uses the left hand to slap the top of the left thigh, making visible contact and producing a sharp slap sound exactly at impact. After that, the person clearly says the single word “help” with no extra words. After the final event, no new target action occurs."
  },
  {
    "item_id": "slap-then-help-then-thumbs_up__order",
    "canonical_item_id": "speech_action_silent_action_sounding_rel_order_sounding_action_then_speech_then_silent_action",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "sounding_action",
          "speech",
          "silent_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a single seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person’s left hand strikes the top of the left thigh once, making visible contact and a sharp slap sound. After that, the person clearly says “help” and nothing else. Then the person forms and holds a clear thumbs-up with the right hand, with the thumb extended upward. After the final event, no new target action occurs."
  },
  {
    "item_id": "slap-then-thumbs_up-then-help__order",
    "canonical_item_id": "speech_action_silent_action_sounding_rel_order_sounding_action_then_silent_action_then_speech",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "sounding_action",
          "silent_action",
          "speech"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room with a static medium shot, one seated person faces the camera on a chair with both hands initially resting on the knees or thighs, and the full face, mouth, upper body, both hands, and thighs are clearly visible. First, the person’s left hand strikes the top of the left thigh once with visible contact and a sharp slap sound. After that is completed, the person forms and holds a clear thumbs-up with the right hand, with the thumb extended upward. After that, the person clearly says the single word “help” and nothing else. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop-with-open_palm__sync",
    "canonical_item_id": "stop_open_palm_rel_sync",
    "modality_combination": "Speech + Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action"
        ]
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. At one synchronized moment, the person clearly says the single word “stop” while at the same time holds the right hand in a clear open-palm pose with the palm facing the camera. No additional words or target sounds occur beyond the required ones. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop-with-slap__sync",
    "canonical_item_id": "stop_slap_rel_sync",
    "modality_combination": "Speech + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "sounding_action"
        ]
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. At one synchronized moment, the person clearly says the single word “stop” while at the same time strikes the top of the left thigh with the left hand, producing a sharp slap sound exactly at impact. No additional words or target sounds occur beyond the required ones. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-with-clap__sync",
    "canonical_item_id": "help_clap_rel_sync",
    "modality_combination": "Speech + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "sounding_action"
        ]
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. At one synchronized moment, the person clearly says the single word “help” while at the same time claps both hands together once with a sharp clap sound exactly at contact. No additional words or target sounds occur beyond the required ones. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop-with-thumbs_up-with-slap__sync",
    "canonical_item_id": "stop_thumbs_up_slap_rel_sync",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. At one synchronized moment, the person clearly says the single word “stop”, holds the right hand in a clear thumbs-up pose with the thumb extended upward, and strikes the top of the left thigh with the left hand, producing a sharp slap sound exactly at impact, all at the same time. No additional words or target sounds occur beyond the required ones. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-with-open_palm__sync_count",
    "canonical_item_id": "help_open_palm_rel_sync_count",
    "modality_combination": "Speech + Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action"
        ],
        "count": 2
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. The person performs one synchronized bundle and then repeats it, so the bundle happens exactly 2 times, with only a brief natural reset between repetitions. In each repetition, the person clearly says the single word “help” while at the same moment holds the right hand in a clear open-palm pose with the palm facing the camera. No listed event occurs alone outside the synchronized repetitions, and no extra words or target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop-with-clap__sync_count",
    "canonical_item_id": "stop_clap_rel_sync_count",
    "modality_combination": "Speech + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "sounding_action"
        ],
        "count": 2
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. The person performs one synchronized bundle and then repeats it, so the bundle happens exactly 2 times, with only a brief natural reset between repetitions. In each repetition, the person clearly says the single word “stop” while at the same moment claps both hands together once with a sharp clap sound exactly at contact. No listed event occurs alone outside the synchronized repetitions, and no extra words or target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "open_palm-with-slap__sync_count",
    "canonical_item_id": "open_palm_slap_rel_sync_count",
    "modality_combination": "Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    ],
    "content": {
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "silent_action",
          "sounding_action"
        ],
        "count": 2
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. The person performs one synchronized bundle and then repeats it, so the bundle happens exactly 2 times, with only a brief natural reset between repetitions. In each repetition, the person holds the right hand in a clear open-palm pose with the palm facing the camera while at the same moment strikes the top of the left thigh with the left hand, producing a sharp slap sound exactly at impact. No listed event occurs alone outside the synchronized repetitions, and no extra words or target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-with-open_palm-with-slap__sync_count",
    "canonical_item_id": "help_open_palm_slap_rel_sync_count",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ],
        "count": 2
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. The person performs one synchronized bundle and then repeats it, so the bundle happens exactly 2 times, with only a brief natural reset between repetitions. In each repetition, the person clearly says the single word “help”, holds the right hand in a clear open-palm pose with the palm facing the camera, and strikes the top of the left thigh with the left hand, producing a sharp slap sound exactly at impact all at the same moment. No listed event occurs alone outside the synchronized repetitions, and no extra words or target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "thumbs_up-then-open_palm__order",
    "canonical_item_id": "thumbs_up_open_palm_rel_order_thumbs_up_then_raise_open_palm",
    "modality_combination": "Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "thumbs_up",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      },
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    ],
    "content": {
      "thumbs_up": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      },
      "open_palm": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "thumbs_up",
          "open_palm"
        ]
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person holds the right hand in a clear thumbs-up pose (thumb extended upward). After that is complete, the person holds the right hand in a clear open-palm pose (palm facing the camera). Each event finishes before the next begins, the events do not overlap, and no event is repeated. After the final event, no new target action occurs."
  },
  {
    "item_id": "open_palm-then-thumbs_up__order",
    "canonical_item_id": "thumbs_up_open_palm_rel_order_raise_open_palm_then_thumbs_up",
    "modality_combination": "Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      {
        "id": "thumbs_up",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      }
    ],
    "content": {
      "open_palm": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      "thumbs_up": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "open_palm",
          "thumbs_up"
        ]
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person holds the right hand in a clear open-palm pose (palm facing the camera). After that is complete, the person holds the right hand in a clear thumbs-up pose (thumb extended upward). Each event finishes before the next begins, the events do not overlap, and no event is repeated. After the final event, no new target action occurs."
  },
  {
    "item_id": "open_palm-then-clap__order",
    "canonical_item_id": "open_palm_clap_rel_order_raise_open_palm_then_clapping_hands",
    "modality_combination": "Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      }
    ],
    "content": {
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person holds the right hand in a clear open-palm pose (palm facing the camera). After that is complete, the person claps both hands together once (visible contact, sharp clap sound). Each event finishes before the next begins, the events do not overlap, and no event is repeated. After the final event, no new target action occurs."
  },
  {
    "item_id": "clap-then-open_palm__order",
    "canonical_item_id": "open_palm_clap_rel_order_clapping_hands_then_raise_open_palm",
    "modality_combination": "Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    ],
    "content": {
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "sounding_action",
          "silent_action"
        ]
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person claps both hands together once (visible contact, sharp clap sound). After that is complete, the person holds the right hand in a clear open-palm pose (palm facing the camera). Each event finishes before the next begins, the events do not overlap, and no event is repeated. After the final event, no new target action occurs."
  },
  {
    "item_id": "slap-then-clap__order",
    "canonical_item_id": "slap_clap_rel_order_slapping_the_thigh_then_clapping_hands",
    "modality_combination": "Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      }
    ],
    "content": {
      "slap": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "slap",
          "clap"
        ]
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person strikes the top of the left thigh with the left hand (visible contact, sharp slap sound). After that is complete, the person claps both hands together once (visible contact, sharp clap sound). Each event finishes before the next begins, the events do not overlap, and no event is repeated. After the final event, no new target action occurs."
  },
  {
    "item_id": "clap-then-slap__order",
    "canonical_item_id": "slap_clap_rel_order_clapping_hands_then_slapping_the_thigh",
    "modality_combination": "Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      },
      {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    ],
    "content": {
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      },
      "slap": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "clap",
          "slap"
        ]
      }
    },
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person claps both hands together once (visible contact, sharp clap sound). After that is complete, the person strikes the top of the left thigh with the left hand (visible contact, sharp slap sound). Each event finishes before the next begins, the events do not overlap, and no event is repeated. After the final event, no new target action occurs."
  },
  {
    "item_id": "help_x2-then-slap_x1__order_count",
    "canonical_item_id": "help_x2_then_slap_x1_v4_rel_order_count",
    "modality_combination": "Speech + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_help",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    ],
    "content": {
      "speech_help": {
        "id": "speech_help",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "slap": {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_help",
          "slap"
        ],
        "event_counts": {
          "speech_help": 2,
          "slap": 1
        },
        "expanded_sequence": [
          "speech_help",
          "speech_help",
          "slap"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must say the single word “help” exactly 2 times. After all help repetitions are complete, the person must slap the top of the left thigh with the left hand, producing one sharp slap sound at impact once. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "help_x1-then-slap_x2__order_count",
    "canonical_item_id": "help_x1_then_slap_x2_v4_rel_order_count",
    "modality_combination": "Speech + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_help",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    ],
    "content": {
      "speech_help": {
        "id": "speech_help",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "slap": {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_help",
          "slap"
        ],
        "event_counts": {
          "speech_help": 1,
          "slap": 2
        },
        "expanded_sequence": [
          "speech_help",
          "slap",
          "slap"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must say the single word “help” once. After all help repetitions are complete, the person must slap the top of the left thigh with the left hand, producing one sharp slap sound at impact exactly 2 times. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "slap_x2-then-help_x1__order_count",
    "canonical_item_id": "slap_x2_then_help_x1_v4_rel_order_count",
    "modality_combination": "Action (sounding) + Speech",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      },
      {
        "id": "speech_help",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      }
    ],
    "content": {
      "slap": {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      },
      "speech_help": {
        "id": "speech_help",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "slap",
          "speech_help"
        ],
        "event_counts": {
          "slap": 2,
          "speech_help": 1
        },
        "expanded_sequence": [
          "slap",
          "slap",
          "speech_help"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must slap the top of the left thigh with the left hand, producing one sharp slap sound at impact exactly 2 times. After all slap repetitions are complete, the person must say the single word “help” once. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "slap_x1-then-help_x2__order_count",
    "canonical_item_id": "slap_x1_then_help_x2_v4_rel_order_count",
    "modality_combination": "Action (sounding) + Speech",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      },
      {
        "id": "speech_help",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      }
    ],
    "content": {
      "slap": {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      },
      "speech_help": {
        "id": "speech_help",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "slap",
          "speech_help"
        ],
        "event_counts": {
          "slap": 1,
          "speech_help": 2
        },
        "expanded_sequence": [
          "slap",
          "speech_help",
          "speech_help"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must slap the top of the left thigh with the left hand, producing one sharp slap sound at impact once. After all slap repetitions are complete, the person must say the single word “help” exactly 2 times. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop_x2-then-open_palm_x1__order_count",
    "canonical_item_id": "stop_x2_then_open_palm_x1_v4_rel_order_count",
    "modality_combination": "Speech + Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    ],
    "content": {
      "speech_stop": {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "open_palm": {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_stop",
          "open_palm"
        ],
        "event_counts": {
          "speech_stop": 2,
          "open_palm": 1
        },
        "expanded_sequence": [
          "speech_stop",
          "speech_stop",
          "open_palm"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must say the single word “stop” exactly 2 times. After all stop repetitions are complete, the person must hold the right hand in a clear open-palm pose facing the camera once. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop_x1-then-open_palm_x2__order_count",
    "canonical_item_id": "stop_x1_then_open_palm_x2_v4_rel_order_count",
    "modality_combination": "Speech + Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    ],
    "content": {
      "speech_stop": {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "open_palm": {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_stop",
          "open_palm"
        ],
        "event_counts": {
          "speech_stop": 1,
          "open_palm": 2
        },
        "expanded_sequence": [
          "speech_stop",
          "open_palm",
          "open_palm"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must say the single word “stop” once. After all stop repetitions are complete, the person must hold the right hand in a clear open-palm pose facing the camera exactly 2 times. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "open_palm_x2-then-stop_x1__order_count",
    "canonical_item_id": "open_palm_x2_then_stop_x1_v4_rel_order_count",
    "modality_combination": "Action (silent) + Speech",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      }
    ],
    "content": {
      "open_palm": {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      "speech_stop": {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "open_palm",
          "speech_stop"
        ],
        "event_counts": {
          "open_palm": 2,
          "speech_stop": 1
        },
        "expanded_sequence": [
          "open_palm",
          "open_palm",
          "speech_stop"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must hold the right hand in a clear open-palm pose facing the camera exactly 2 times. After all open_palm repetitions are complete, the person must say the single word “stop” once. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "open_palm_x1-then-stop_x2__order_count",
    "canonical_item_id": "open_palm_x1_then_stop_x2_v4_rel_order_count",
    "modality_combination": "Action (silent) + Speech",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      }
    ],
    "content": {
      "open_palm": {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      "speech_stop": {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "open_palm",
          "speech_stop"
        ],
        "event_counts": {
          "open_palm": 1,
          "speech_stop": 2
        },
        "expanded_sequence": [
          "open_palm",
          "speech_stop",
          "speech_stop"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must hold the right hand in a clear open-palm pose facing the camera once. After all open_palm repetitions are complete, the person must say the single word “stop” exactly 2 times. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "thumbs_up_x2-then-clap_x1__order_count",
    "canonical_item_id": "thumbs_up_x2_then_clap_x1_v4_rel_order_count",
    "modality_combination": "Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "thumbs_up",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      }
    ],
    "content": {
      "thumbs_up": {
        "id": "thumbs_up",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      },
      "clap": {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "thumbs_up",
          "clap"
        ],
        "event_counts": {
          "thumbs_up": 2,
          "clap": 1
        },
        "expanded_sequence": [
          "thumbs_up",
          "thumbs_up",
          "clap"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must make a clear right-hand thumbs-up pose exactly 2 times. After all thumbs_up repetitions are complete, the person must clap both hands together once, producing one sharp clap sound at impact once. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "thumbs_up_x1-then-clap_x2__order_count",
    "canonical_item_id": "thumbs_up_x1_then_clap_x2_v4_rel_order_count",
    "modality_combination": "Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "thumbs_up",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      }
    ],
    "content": {
      "thumbs_up": {
        "id": "thumbs_up",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      },
      "clap": {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "thumbs_up",
          "clap"
        ],
        "event_counts": {
          "thumbs_up": 1,
          "clap": 2
        },
        "expanded_sequence": [
          "thumbs_up",
          "clap",
          "clap"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must make a clear right-hand thumbs-up pose once. After all thumbs_up repetitions are complete, the person must clap both hands together once, producing one sharp clap sound at impact exactly 2 times. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "clap_x2-then-thumbs_up_x1__order_count",
    "canonical_item_id": "clap_x2_then_thumbs_up_x1_v4_rel_order_count",
    "modality_combination": "Action (sounding) + Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      },
      {
        "id": "thumbs_up",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      }
    ],
    "content": {
      "clap": {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      },
      "thumbs_up": {
        "id": "thumbs_up",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "clap",
          "thumbs_up"
        ],
        "event_counts": {
          "clap": 2,
          "thumbs_up": 1
        },
        "expanded_sequence": [
          "clap",
          "clap",
          "thumbs_up"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must clap both hands together once, producing one sharp clap sound at impact exactly 2 times. After all clap repetitions are complete, the person must make a clear right-hand thumbs-up pose once. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "clap_x1-then-thumbs_up_x2__order_count",
    "canonical_item_id": "clap_x1_then_thumbs_up_x2_v4_rel_order_count",
    "modality_combination": "Action (sounding) + Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      },
      {
        "id": "thumbs_up",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      }
    ],
    "content": {
      "clap": {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hand",
        "target_body_side": "both",
        "target_body_part": "hand",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together in front of the torso to clap, with visible hand-to-hand contact and a single sharp clap sound at the moment of impact."
      },
      "thumbs_up": {
        "id": "thumbs_up",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable. The target is the pose, not a separate hand-raising motion."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "clap",
          "thumbs_up"
        ],
        "event_counts": {
          "clap": 1,
          "thumbs_up": 2
        },
        "expanded_sequence": [
          "clap",
          "thumbs_up",
          "thumbs_up"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must clap both hands together once, producing one sharp clap sound at impact once. After all clap repetitions are complete, the person must make a clear right-hand thumbs-up pose exactly 2 times. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "open_palm_x2-then-slap_x1__order_count",
    "canonical_item_id": "open_palm_x2_then_slap_x1_v4_rel_order_count",
    "modality_combination": "Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    ],
    "content": {
      "open_palm": {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      "slap": {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "open_palm",
          "slap"
        ],
        "event_counts": {
          "open_palm": 2,
          "slap": 1
        },
        "expanded_sequence": [
          "open_palm",
          "open_palm",
          "slap"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must hold the right hand in a clear open-palm pose facing the camera exactly 2 times. After all open_palm repetitions are complete, the person must slap the top of the left thigh with the left hand, producing one sharp slap sound at impact once. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "open_palm_x1-then-slap_x2__order_count",
    "canonical_item_id": "open_palm_x1_then_slap_x2_v4_rel_order_count",
    "modality_combination": "Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    ],
    "content": {
      "open_palm": {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      },
      "slap": {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "open_palm",
          "slap"
        ],
        "event_counts": {
          "open_palm": 1,
          "slap": 2
        },
        "expanded_sequence": [
          "open_palm",
          "slap",
          "slap"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must hold the right hand in a clear open-palm pose facing the camera once. After all open_palm repetitions are complete, the person must slap the top of the left thigh with the left hand, producing one sharp slap sound at impact exactly 2 times. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "slap_x2-then-open_palm_x1__order_count",
    "canonical_item_id": "slap_x2_then_open_palm_x1_v4_rel_order_count",
    "modality_combination": "Action (sounding) + Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      },
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    ],
    "content": {
      "slap": {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      },
      "open_palm": {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "slap",
          "open_palm"
        ],
        "event_counts": {
          "slap": 2,
          "open_palm": 1
        },
        "expanded_sequence": [
          "slap",
          "slap",
          "open_palm"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must slap the top of the left thigh with the left hand, producing one sharp slap sound at impact exactly 2 times. After all slap repetitions are complete, the person must hold the right hand in a clear open-palm pose facing the camera once. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "slap_x1-then-open_palm_x2__order_count",
    "canonical_item_id": "slap_x1_then_open_palm_x2_v4_rel_order_count",
    "modality_combination": "Action (sounding) + Action (silent)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      },
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    ],
    "content": {
      "slap": {
        "id": "slap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the left thigh, with visible contact and a sharp slap sound at the moment of impact."
      },
      "open_palm": {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers together and extended, held clearly as a recognizable open-palm pose. The target is the held pose, not a separate raising motion."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "slap",
          "open_palm"
        ],
        "event_counts": {
          "slap": 1,
          "open_palm": 2
        },
        "expanded_sequence": [
          "slap",
          "open_palm",
          "open_palm"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. Person A starts seated on a chair with both hands resting on the knees or thighs. First, the person must slap the top of the left thigh with the left hand, producing one sharp slap sound at impact once. After all slap repetitions are complete, the person must hold the right hand in a clear open-palm pose facing the camera exactly 2 times. The order must be strict: all repetitions of the first event happen before any repetition of the second event begins. No extra target events, extra words, or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "clap-then-peace_sign-then-help__order",
    "canonical_item_id": "help_peace_sign_clap_rel_order_clap_then_peace_sign_then_help",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "sounding_action",
          "silent_action",
          "speech"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person claps both hands together, producing a sharp clap sound at contact once. Next, the person forms and holds a clear right-hand peace sign once. Finally, the person says the single word “help” once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "thumbs_up-then-clap-then-stop__order",
    "canonical_item_id": "stop_thumbs_up_clap_rel_order_thumbs_up_then_clap_then_stop",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "silent_action",
          "sounding_action",
          "speech"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person forms and holds a clear right-hand thumbs-up once. Next, the person claps both hands together, producing a sharp clap sound at contact once. Finally, the person says the single word “stop” once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop_x2-then-open_palm_x1-then-clap_x1__order_count",
    "canonical_item_id": "stop_open_palm_clap_rel_order_count_stop_then_stop_then_open_palm_then_clap",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_stop": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "open_palm": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_stop",
          "open_palm",
          "clap"
        ],
        "event_counts": {
          "speech_stop": 2,
          "open_palm": 1,
          "clap": 1
        },
        "expanded_sequence": [
          "speech_stop",
          "speech_stop",
          "open_palm",
          "clap"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “stop” exactly 2 times. Next, the person forms and holds a clear right-hand open-palm pose facing the camera once. Finally, the person claps both hands together, producing a sharp clap sound at contact once. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "open_palm-then-clap-then-stop__order",
    "canonical_item_id": "stop_open_palm_clap_rel_order_open_palm_then_clap_then_stop",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "silent_action",
          "sounding_action",
          "speech"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person forms and holds a clear right-hand open-palm pose facing the camera once. Next, the person claps both hands together, producing a sharp clap sound at contact once. Finally, the person says the single word “stop” once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "clap-then-stop-then-open_palm__order",
    "canonical_item_id": "stop_open_palm_clap_rel_order_clap_then_stop_then_open_palm",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "sounding_action",
          "speech",
          "silent_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person claps both hands together, producing a sharp clap sound at contact once. Next, the person says the single word “stop” once. Finally, the person forms and holds a clear right-hand open-palm pose facing the camera once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop_x1-then-peace_sign_x2-then-clap_x1__order_count",
    "canonical_item_id": "stop_peace_sign_clap_rel_order_count_stop_then_peace_sign_then_peace_sign_then_clap",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_stop": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_stop",
          "peace_sign",
          "clap"
        ],
        "event_counts": {
          "speech_stop": 1,
          "peace_sign": 2,
          "clap": 1
        },
        "expanded_sequence": [
          "speech_stop",
          "peace_sign",
          "peace_sign",
          "clap"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “stop” once. Next, the person forms and holds a clear right-hand peace sign exactly 2 times. Finally, the person claps both hands together, producing a sharp clap sound at contact once. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop-then-clap-then-peace_sign__order",
    "canonical_item_id": "stop_peace_sign_clap_rel_order_stop_then_clap_then_peace_sign",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "speech",
          "sounding_action",
          "silent_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “stop” once. Next, the person claps both hands together, producing a sharp clap sound at contact once. Finally, the person forms and holds a clear right-hand peace sign once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop_x1-then-clap_x1-then-peace_sign_x2__order_count",
    "canonical_item_id": "stop_peace_sign_clap_rel_order_count_stop_then_clap_then_peace_sign_then_peace_sign",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_stop": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_stop",
          "clap",
          "peace_sign"
        ],
        "event_counts": {
          "speech_stop": 1,
          "clap": 1,
          "peace_sign": 2
        },
        "expanded_sequence": [
          "speech_stop",
          "clap",
          "peace_sign",
          "peace_sign"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “stop” once. Next, the person claps both hands together, producing a sharp clap sound at contact once. Finally, the person forms and holds a clear right-hand peace sign exactly 2 times. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop_x1-then-clap_x2-then-peace_sign_x1__order_count",
    "canonical_item_id": "stop_peace_sign_clap_rel_order_count_stop_then_clap_then_clap_then_peace_sign",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_stop": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_stop",
          "clap",
          "peace_sign"
        ],
        "event_counts": {
          "speech_stop": 1,
          "clap": 2,
          "peace_sign": 1
        },
        "expanded_sequence": [
          "speech_stop",
          "clap",
          "clap",
          "peace_sign"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “stop” once. Next, the person claps both hands together, producing a sharp clap sound at contact exactly 2 times. Finally, the person forms and holds a clear right-hand peace sign once. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "peace_sign-then-stop-then-clap__order",
    "canonical_item_id": "stop_peace_sign_clap_rel_order_peace_sign_then_stop_then_clap",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "silent_action",
          "speech",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person forms and holds a clear right-hand peace sign once. Next, the person says the single word “stop” once. Finally, the person claps both hands together, producing a sharp clap sound at contact once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "peace_sign_x2-then-stop_x1-then-clap_x1__order_count",
    "canonical_item_id": "stop_peace_sign_clap_rel_order_count_peace_sign_then_peace_sign_then_stop_then_clap",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_stop": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "peace_sign",
          "speech_stop",
          "clap"
        ],
        "event_counts": {
          "peace_sign": 2,
          "speech_stop": 1,
          "clap": 1
        },
        "expanded_sequence": [
          "peace_sign",
          "peace_sign",
          "speech_stop",
          "clap"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person forms and holds a clear right-hand peace sign exactly 2 times. Next, the person says the single word “stop” once. Finally, the person claps both hands together, producing a sharp clap sound at contact once. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "peace_sign_x1-then-clap_x1-then-stop_x2__order_count",
    "canonical_item_id": "stop_peace_sign_clap_rel_order_count_peace_sign_then_clap_then_stop_then_stop",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_stop": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "peace_sign",
          "clap",
          "speech_stop"
        ],
        "event_counts": {
          "peace_sign": 1,
          "clap": 1,
          "speech_stop": 2
        },
        "expanded_sequence": [
          "peace_sign",
          "clap",
          "speech_stop",
          "speech_stop"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person forms and holds a clear right-hand peace sign once. Next, the person claps both hands together, producing a sharp clap sound at contact once. Finally, the person says the single word “stop” exactly 2 times. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "peace_sign_x1-then-clap_x2-then-stop_x1__order_count",
    "canonical_item_id": "stop_peace_sign_clap_rel_order_count_peace_sign_then_clap_then_clap_then_stop",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_stop": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "peace_sign",
          "clap",
          "speech_stop"
        ],
        "event_counts": {
          "peace_sign": 1,
          "clap": 2,
          "speech_stop": 1
        },
        "expanded_sequence": [
          "peace_sign",
          "clap",
          "clap",
          "speech_stop"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person forms and holds a clear right-hand peace sign once. Next, the person claps both hands together, producing a sharp clap sound at contact exactly 2 times. Finally, the person says the single word “stop” once. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "clap_x2-then-stop_x1-then-peace_sign_x1__order_count",
    "canonical_item_id": "stop_peace_sign_clap_rel_order_count_clap_then_clap_then_stop_then_peace_sign",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_stop",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_stop": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "clap",
          "speech_stop",
          "peace_sign"
        ],
        "event_counts": {
          "clap": 2,
          "speech_stop": 1,
          "peace_sign": 1
        },
        "expanded_sequence": [
          "clap",
          "clap",
          "speech_stop",
          "peace_sign"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person claps both hands together, producing a sharp clap sound at contact exactly 2 times. Next, the person says the single word “stop” once. Finally, the person forms and holds a clear right-hand peace sign once. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "clap-then-peace_sign-then-stop__order",
    "canonical_item_id": "stop_peace_sign_clap_rel_order_clap_then_peace_sign_then_stop",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "sounding_action",
          "silent_action",
          "speech"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person claps both hands together, producing a sharp clap sound at contact once. Next, the person forms and holds a clear right-hand peace sign once. Finally, the person says the single word “stop” once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "thumbs_up-then-okay-then-clap__order",
    "canonical_item_id": "okay_thumbs_up_clap_rel_order_thumbs_up_then_okay_then_clap",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "silent_action",
          "speech",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person forms and holds a clear right-hand thumbs-up once. Next, the person says the single word “okay” once. Finally, the person claps both hands together, producing a sharp clap sound at contact once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "clap-then-okay-then-thumbs_up__order",
    "canonical_item_id": "okay_thumbs_up_clap_rel_order_clap_then_okay_then_thumbs_up",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "sounding_action",
          "speech",
          "silent_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person claps both hands together, producing a sharp clap sound at contact once. Next, the person says the single word “okay” once. Finally, the person forms and holds a clear right-hand thumbs-up once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay-then-open_palm-then-clap__order",
    "canonical_item_id": "okay_open_palm_clap_rel_order_okay_then_open_palm_then_clap",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "speech",
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “okay” once. Next, the person forms and holds a clear right-hand open-palm pose facing the camera once. Finally, the person claps both hands together, producing a sharp clap sound at contact once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay-then-clap-then-open_palm__order",
    "canonical_item_id": "okay_open_palm_clap_rel_order_okay_then_clap_then_open_palm",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "speech",
          "sounding_action",
          "silent_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “okay” once. Next, the person claps both hands together, producing a sharp clap sound at contact once. Finally, the person forms and holds a clear right-hand open-palm pose facing the camera once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay_x1-then-clap_x1-then-open_palm_x2__order_count",
    "canonical_item_id": "okay_open_palm_clap_rel_order_count_okay_then_clap_then_open_palm_then_open_palm",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_okay",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_okay": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "open_palm": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_okay",
          "clap",
          "open_palm"
        ],
        "event_counts": {
          "speech_okay": 1,
          "clap": 1,
          "open_palm": 2
        },
        "expanded_sequence": [
          "speech_okay",
          "clap",
          "open_palm",
          "open_palm"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “okay” once. Next, the person claps both hands together, producing a sharp clap sound at contact once. Finally, the person forms and holds a clear right-hand open-palm pose facing the camera exactly 2 times. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay_x1-then-clap_x2-then-open_palm_x1__order_count",
    "canonical_item_id": "okay_open_palm_clap_rel_order_count_okay_then_clap_then_clap_then_open_palm",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_okay",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_okay": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "open_palm": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_okay",
          "clap",
          "open_palm"
        ],
        "event_counts": {
          "speech_okay": 1,
          "clap": 2,
          "open_palm": 1
        },
        "expanded_sequence": [
          "speech_okay",
          "clap",
          "clap",
          "open_palm"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “okay” once. Next, the person claps both hands together, producing a sharp clap sound at contact exactly 2 times. Finally, the person forms and holds a clear right-hand open-palm pose facing the camera once. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "open_palm-then-okay-then-clap__order",
    "canonical_item_id": "okay_open_palm_clap_rel_order_open_palm_then_okay_then_clap",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "silent_action",
          "speech",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person forms and holds a clear right-hand open-palm pose facing the camera once. Next, the person says the single word “okay” once. Finally, the person claps both hands together, producing a sharp clap sound at contact once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "clap_x2-then-okay_x1-then-open_palm_x1__order_count",
    "canonical_item_id": "okay_open_palm_clap_rel_order_count_clap_then_clap_then_okay_then_open_palm",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_okay",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "open_palm",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_okay": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "open_palm": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "clap",
          "speech_okay",
          "open_palm"
        ],
        "event_counts": {
          "clap": 2,
          "speech_okay": 1,
          "open_palm": 1
        },
        "expanded_sequence": [
          "clap",
          "clap",
          "speech_okay",
          "open_palm"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person claps both hands together, producing a sharp clap sound at contact exactly 2 times. Next, the person says the single word “okay” once. Finally, the person forms and holds a clear right-hand open-palm pose facing the camera once. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay-then-peace_sign-then-clap__order",
    "canonical_item_id": "okay_peace_sign_clap_rel_order_okay_then_peace_sign_then_clap",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "speech",
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “okay” once. Next, the person forms and holds a clear right-hand peace sign once. Finally, the person claps both hands together, producing a sharp clap sound at contact once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay_x1-then-peace_sign_x2-then-clap_x1__order_count",
    "canonical_item_id": "okay_peace_sign_clap_rel_order_count_okay_then_peace_sign_then_peace_sign_then_clap",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_okay",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_okay": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_okay",
          "peace_sign",
          "clap"
        ],
        "event_counts": {
          "speech_okay": 1,
          "peace_sign": 2,
          "clap": 1
        },
        "expanded_sequence": [
          "speech_okay",
          "peace_sign",
          "peace_sign",
          "clap"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “okay” once. Next, the person forms and holds a clear right-hand peace sign exactly 2 times. Finally, the person claps both hands together, producing a sharp clap sound at contact once. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay_x1-then-peace_sign_x1-then-clap_x2__order_count",
    "canonical_item_id": "okay_peace_sign_clap_rel_order_count_okay_then_peace_sign_then_clap_then_clap",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_okay",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_okay": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_okay",
          "peace_sign",
          "clap"
        ],
        "event_counts": {
          "speech_okay": 1,
          "peace_sign": 1,
          "clap": 2
        },
        "expanded_sequence": [
          "speech_okay",
          "peace_sign",
          "clap",
          "clap"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “okay” once. Next, the person forms and holds a clear right-hand peace sign once. Finally, the person claps both hands together, producing a sharp clap sound at contact exactly 2 times. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay-then-clap-then-peace_sign__order",
    "canonical_item_id": "okay_peace_sign_clap_rel_order_okay_then_clap_then_peace_sign",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "speech",
          "sounding_action",
          "silent_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “okay” once. Next, the person claps both hands together, producing a sharp clap sound at contact once. Finally, the person forms and holds a clear right-hand peace sign once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay_x1-then-clap_x1-then-peace_sign_x2__order_count",
    "canonical_item_id": "okay_peace_sign_clap_rel_order_count_okay_then_clap_then_peace_sign_then_peace_sign",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_okay",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_okay": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_okay",
          "clap",
          "peace_sign"
        ],
        "event_counts": {
          "speech_okay": 1,
          "clap": 1,
          "peace_sign": 2
        },
        "expanded_sequence": [
          "speech_okay",
          "clap",
          "peace_sign",
          "peace_sign"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “okay” once. Next, the person claps both hands together, producing a sharp clap sound at contact once. Finally, the person forms and holds a clear right-hand peace sign exactly 2 times. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay_x1-then-clap_x2-then-peace_sign_x1__order_count",
    "canonical_item_id": "okay_peace_sign_clap_rel_order_count_okay_then_clap_then_clap_then_peace_sign",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_okay",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_okay": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "speech_okay",
          "clap",
          "peace_sign"
        ],
        "event_counts": {
          "speech_okay": 1,
          "clap": 2,
          "peace_sign": 1
        },
        "expanded_sequence": [
          "speech_okay",
          "clap",
          "clap",
          "peace_sign"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person says the single word “okay” once. Next, the person claps both hands together, producing a sharp clap sound at contact exactly 2 times. Finally, the person forms and holds a clear right-hand peace sign once. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "peace_sign_x1-then-okay_x1-then-clap_x2__order_count",
    "canonical_item_id": "okay_peace_sign_clap_rel_order_count_peace_sign_then_okay_then_clap_then_clap",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_okay",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_okay": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "peace_sign",
          "speech_okay",
          "clap"
        ],
        "event_counts": {
          "peace_sign": 1,
          "speech_okay": 1,
          "clap": 2
        },
        "expanded_sequence": [
          "peace_sign",
          "speech_okay",
          "clap",
          "clap"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person forms and holds a clear right-hand peace sign once. Next, the person says the single word “okay” once. Finally, the person claps both hands together, producing a sharp clap sound at contact exactly 2 times. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "peace_sign-then-clap-then-okay__order",
    "canonical_item_id": "okay_peace_sign_clap_rel_order_peace_sign_then_clap_then_okay",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "silent_action",
          "sounding_action",
          "speech"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person forms and holds a clear right-hand peace sign once. Next, the person claps both hands together, producing a sharp clap sound at contact once. Finally, the person says the single word “okay” once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "peace_sign_x1-then-clap_x1-then-okay_x2__order_count",
    "canonical_item_id": "okay_peace_sign_clap_rel_order_count_peace_sign_then_clap_then_okay_then_okay",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_okay",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_okay": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "peace_sign",
          "clap",
          "speech_okay"
        ],
        "event_counts": {
          "peace_sign": 1,
          "clap": 1,
          "speech_okay": 2
        },
        "expanded_sequence": [
          "peace_sign",
          "clap",
          "speech_okay",
          "speech_okay"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person forms and holds a clear right-hand peace sign once. Next, the person claps both hands together, producing a sharp clap sound at contact once. Finally, the person says the single word “okay” exactly 2 times. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "peace_sign_x2-then-clap_x1-then-okay_x1__order_count",
    "canonical_item_id": "okay_peace_sign_clap_rel_order_count_peace_sign_then_peace_sign_then_clap_then_okay",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech_okay",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "peace_sign",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "clap",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech_okay": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "peace_sign": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "clap": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order_count",
      "timing_type": "relative",
      "value": {
        "ordered_events": [
          "peace_sign",
          "clap",
          "speech_okay"
        ],
        "event_counts": {
          "peace_sign": 2,
          "clap": 1,
          "speech_okay": 1
        },
        "expanded_sequence": [
          "peace_sign",
          "peace_sign",
          "clap",
          "speech_okay"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person forms and holds a clear right-hand peace sign exactly 2 times. Next, the person claps both hands together, producing a sharp clap sound at contact once. Finally, the person says the single word “okay” once. All repetitions of an event are completed before the next event begins, and the order is strict. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "clap-then-okay-then-peace_sign__order",
    "canonical_item_id": "okay_peace_sign_clap_rel_order_clap_then_okay_then_peace_sign",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "sounding_action",
          "speech",
          "silent_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person claps both hands together, producing a sharp clap sound at contact once. Next, the person says the single word “okay” once. Finally, the person forms and holds a clear right-hand peace sign once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "clap-then-peace_sign-then-okay__order",
    "canonical_item_id": "okay_peace_sign_clap_rel_order_clap_then_peace_sign_then_okay",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "clapping_hands",
        "acting_body_side": "both",
        "acting_body_part": "hands",
        "target_sound": "sharp clap sound",
        "definition": "The person brings both hands together once so that the palms make visible contact and a sharp clap sound occurs exactly at the moment of contact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "sounding_action",
          "silent_action",
          "speech"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person claps both hands together, producing a sharp clap sound at contact once. Next, the person forms and holds a clear right-hand peace sign once. Finally, the person says the single word “okay” once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "slap-then-peace_sign-then-okay__order",
    "canonical_item_id": "okay_peace_sign_slap_rel_order_slap_then_peace_sign_then_okay",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "order",
      "timing_type": "relative",
      "value": {
        "sequence": [
          "sounding_action",
          "silent_action",
          "speech"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. First, the person strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact once. Next, the person forms and holds a clear right-hand peace sign once. Finally, the person says the single word “okay” once. The order is strict, and each event begins only after the preceding event is complete. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-with-open_palm-with-slap__sync",
    "canonical_item_id": "help_open_palm_slap_rel_sync",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. At one synchronized moment, the person clearly says the single word “help” while forms and holds a clear right-hand open-palm pose facing the camera and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. All three required events occur together, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-with-peace_sign-with-slap__sync",
    "canonical_item_id": "help_peace_sign_slap_rel_sync",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. At one synchronized moment, the person clearly says the single word “help” while forms and holds a clear right-hand peace sign and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. All three required events occur together, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "help-with-peace_sign-with-slap__sync_count",
    "canonical_item_id": "help_peace_sign_slap_rel_sync_count_x2",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "help",
        "definition": "The person clearly says the single word \"help\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ],
        "count": 2
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. The person performs one synchronized bundle and then repeats it, so the bundle happens exactly 2 times. In each repetition, the person clearly says the single word “help” while forms and holds a clear right-hand peace sign and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. Only a brief natural reset occurs between repetitions, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop-with-thumbs_up-with-slap__sync_count",
    "canonical_item_id": "stop_thumbs_up_slap_rel_sync_count_x2",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ],
        "count": 2
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. The person performs one synchronized bundle and then repeats it, so the bundle happens exactly 2 times. In each repetition, the person clearly says the single word “stop” while forms and holds a clear right-hand thumbs-up and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. Only a brief natural reset occurs between repetitions, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop-with-open_palm-with-slap__sync",
    "canonical_item_id": "stop_open_palm_slap_rel_sync",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. At one synchronized moment, the person clearly says the single word “stop” while forms and holds a clear right-hand open-palm pose facing the camera and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. All three required events occur together, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop-with-open_palm-with-slap__sync_count",
    "canonical_item_id": "stop_open_palm_slap_rel_sync_count_x2",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ],
        "count": 2
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. The person performs one synchronized bundle and then repeats it, so the bundle happens exactly 2 times. In each repetition, the person clearly says the single word “stop” while forms and holds a clear right-hand open-palm pose facing the camera and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. Only a brief natural reset occurs between repetitions, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop-with-peace_sign-with-slap__sync",
    "canonical_item_id": "stop_peace_sign_slap_rel_sync",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. At one synchronized moment, the person clearly says the single word “stop” while forms and holds a clear right-hand peace sign and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. All three required events occur together, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "stop-with-peace_sign-with-slap__sync_count",
    "canonical_item_id": "stop_peace_sign_slap_rel_sync_count_x2",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "stop",
        "definition": "The person clearly says the single word \"stop\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ],
        "count": 2
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. The person performs one synchronized bundle and then repeats it, so the bundle happens exactly 2 times. In each repetition, the person clearly says the single word “stop” while forms and holds a clear right-hand peace sign and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. Only a brief natural reset occurs between repetitions, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay-with-thumbs_up-with-slap__sync",
    "canonical_item_id": "okay_thumbs_up_slap_rel_sync",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. At one synchronized moment, the person clearly says the single word “okay” while forms and holds a clear right-hand thumbs-up and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. All three required events occur together, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay-with-thumbs_up-with-slap__sync_count",
    "canonical_item_id": "okay_thumbs_up_slap_rel_sync_count_x2",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "thumbs_up",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms or holds a thumbs-up pose: a fist closed with the thumb extended upward, clearly recognizable as a thumbs-up. The target is the pose, not a separate upward hand-raising motion."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ],
        "count": 2
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. The person performs one synchronized bundle and then repeats it, so the bundle happens exactly 2 times. In each repetition, the person clearly says the single word “okay” while forms and holds a clear right-hand thumbs-up and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. Only a brief natural reset occurs between repetitions, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay-with-open_palm-with-slap__sync",
    "canonical_item_id": "okay_open_palm_slap_rel_sync",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. At one synchronized moment, the person clearly says the single word “okay” while forms and holds a clear right-hand open-palm pose facing the camera and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. All three required events occur together, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay-with-open_palm-with-slap__sync_count",
    "canonical_item_id": "okay_open_palm_slap_rel_sync_count_x2",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "raise_open_palm",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand is raised to about shoulder height with the palm open and facing the camera, fingers extended, and the pose held clearly enough to be recognized as an open-palm gesture."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ],
        "count": 2
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. The person performs one synchronized bundle and then repeats it, so the bundle happens exactly 2 times. In each repetition, the person clearly says the single word “okay” while forms and holds a clear right-hand open-palm pose facing the camera and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. Only a brief natural reset occurs between repetitions, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay-with-peace_sign-with-slap__sync",
    "canonical_item_id": "okay_peace_sign_slap_rel_sync",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "synchronization",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ]
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. At one synchronized moment, the person clearly says the single word “okay” while forms and holds a clear right-hand peace sign and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. All three required events occur together, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  },
  {
    "item_id": "okay-with-peace_sign-with-slap__sync_count",
    "canonical_item_id": "okay_peace_sign_slap_rel_sync_count_x2",
    "modality_combination": "Speech + Action (silent) + Action (sounding)",
    "subjects": [
      {
        "id": "person_A",
        "description": "one seated person facing the camera",
        "initial_pose": "seated on a chair with both hands initially resting on the knees or thighs",
        "visibility": "full face, mouth, upper body, both hands, and thighs visible during target events"
      }
    ],
    "events": [
      {
        "id": "speech",
        "modality": "speech",
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      {
        "id": "silent_action",
        "modality": "silent_action",
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      {
        "id": "sounding_action",
        "modality": "sounding_action",
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    ],
    "content": {
      "speech": {
        "actor": "person_A",
        "text": "okay",
        "definition": "The person clearly says the single word \"okay\". The speech is audible and easy to distinguish. No extra words are spoken unless explicitly required."
      },
      "silent_action": {
        "actor": "person_A",
        "action": "peace_sign",
        "body_side": "right",
        "body_part": "hand",
        "definition": "The person's right hand forms and holds a clear peace sign: the index and middle fingers are extended and separated in a V shape while the remaining fingers are folded, clearly recognizable as a right-hand peace sign."
      },
      "sounding_action": {
        "actor": "person_A",
        "action": "slapping_the_thigh",
        "acting_body_side": "left",
        "acting_body_part": "hand",
        "target_body_side": "left",
        "target_body_part": "thigh",
        "target_sound": "sharp slap sound",
        "definition": "The person's left hand strikes the top of the person's left thigh. Visible contact is made with the thigh, and a sharp slap sound occurs exactly at the moment of impact."
      }
    },
    "temporal_constraint": {
      "relation_type": "sync_count",
      "timing_type": "relative",
      "value": {
        "events": [
          "speech",
          "silent_action",
          "sounding_action"
        ],
        "count": 2
      }
    },
    "scene_hint": "plain indoor room",
    "camera_hint": "static medium shot",
    "generated_prompt": "In a plain indoor room, a seated person faces the camera in a static medium shot, with the full face, mouth, upper body, both hands, and thighs clearly visible. The person starts seated on a chair with both hands resting on the knees or thighs. The person performs one synchronized bundle and then repeats it, so the bundle happens exactly 2 times. In each repetition, the person clearly says the single word “okay” while forms and holds a clear right-hand peace sign and strikes the top of the left thigh with the left hand, producing a sharp slap sound at contact. Only a brief natural reset occurs between repetitions, and no listed event occurs alone. No extra words or extra target sounds occur. After the final event, no new target action occurs."
  }
]