#include "bits/stdc++.h"
#pragma GCC optimize ("O3")
#pragma GCC target ("sse4")
 
using namespace std;
 
typedef long long ll;
typedef long double ld;
typedef complex<ld> cd;
 
typedef pair<int, int> pi;
typedef pair<ll,ll> pl;
typedef pair<ld,ld> pd;
 
typedef vector<int> vi;
typedef vector<ld> vd;
typedef vector<ll> vl;
typedef vector<pi> vpi;
typedef vector<pl> vpl;
typedef vector<cd> vcd;

template<class T> using pq = priority_queue<T>;
template<class T> using pqg = priority_queue<T, vector<T>, greater<T>>;
 
#define FOR(i, a, b) for (int i=a; i<(b); i++)
#define F0R(i, a) for (int i=0; i<(a); i++)
#define FORd(i,a,b) for (int i = (b)-1; i >= a; i--)
#define F0Rd(i,a) for (int i = (a)-1; i >= 0; i--)
#define trav(a,x) for (auto& a : x)
#define uid(a, b) uniform_int_distribution<int>(a, b)(rng)
 
#define sz(x) (int)(x).size()
#define mp make_pair
#define pb push_back
#define f first
#define s second
#define lb lower_bound
#define ub upper_bound
#define all(x) x.begin(), x.end()
#define ins insert

template<class T> bool ckmin(T& a, const T& b) { return b < a ? a = b, 1 : 0; }
template<class T> bool ckmax(T& a, const T& b) { return a < b ? a = b, 1 : 0; }
 
mt19937 rng(chrono::steady_clock::now().time_since_epoch().count());

void __print(int x) {cerr << x;}
void __print(long x) {cerr << x;}
void __print(long long x) {cerr << x;}
void __print(unsigned x) {cerr << x;}
void __print(unsigned long x) {cerr << x;}
void __print(unsigned long long x) {cerr << x;}
void __print(float x) {cerr << x;}
void __print(double x) {cerr << x;}
void __print(long double x) {cerr << x;}
void __print(char x) {cerr << '\'' << x << '\'';}
void __print(const char *x) {cerr << '\"' << x << '\"';}
void __print(const string &x) {cerr << '\"' << x << '\"';}
void __print(bool x) {cerr << (x ? "true" : "false");}

template<typename T, typename V>
void __print(const pair<T, V> &x) {cerr << '{'; __print(x.first); cerr << ", "; __print(x.second); cerr << '}';}
template<typename T>
void __print(const T &x) {int f = 0; cerr << '{'; for (auto &i: x) cerr << (f++ ? ", " : ""), __print(i); cerr << "}";}
void _print() {cerr << "]\n";}
template <typename T, typename... V>
void _print(T t, V... v) {__print(t); if (sizeof...(v)) cerr << ", "; _print(v...);}
#ifdef DEBUG
#define dbg(x...) cerr << "\e[91m"<<__func__<<":"<<__LINE__<<" [" << #x << "] = ["; _print(x); cerr << "\e[39m" << endl;
#else
#define dbg(x...)
#endif


const int MOD = 1000000007;
const char nl = '\n';
const int MX = 100001; 

vl dij(vector<vpl> &graph, int R) {
    int N = sz(graph);
    vl dist(N); F0R(i, N) dist[i] = 1e18;
    dist[R] = 0;
    pqg<pl> q; q.push({0, R});
    while (!q.empty()) {
        auto [d, v] = q.top(); q.pop();
        if (dist[v] != d) continue;
        trav(a, graph[v]) {
            if (ckmin(dist[a.f], d + a.s)) {
                q.push({dist[a.f], a.f});
            }
        }
    }
    return dist;
}

ll dp[5001][5001];

void solve() {
    int N, B, S, R; cin >> N >> B >> S >> R;
    vector<vpl> g(N), gr(N);
    F0R(i, R) {
        int X, Y, Z; cin >> X >> Y >> Z; X--; Y--;
        g[X].pb({Y, Z});
        gr[Y].pb({X, Z});
    }
    vl dist1 = dij(g, B), dist2 = dij(gr, B);
    vl di(B); F0R(i, B) di[i] = dist1[i] + dist2[i];

    sort(all(di));
    ll ps[B+1];
    ps[0] = 0;
    F0R(i, B) {
        ps[i+1] = ps[i] + di[i];
    }
    F0R(i, B+1) F0R(j, S+1) dp[i][j] = 8e18;
    dp[0][0] = 0;
    FOR(i, 1, B+1) {
        FOR(j, 1, S+1) {
            FOR(k, 1, i/j + 1) {
                ckmin(dp[i][j], dp[i-k][j-1] + (ps[i] - ps[i-k]) * (k-1));
            }
        }
    }
    cout << dp[B][S] << nl;

}
 
int main() {
    ios_base::sync_with_stdio(0); cin.tie(0);

    int T = 1;
//    cin >> T;
    while(T--) {
        solve();
    }

	return 0;
}